{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/sentence-classification","name":"Sentence Classification","slug":"sentence-classification","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":303,"papers_with_code":115,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":14,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/sentence-classification-on-scicite","slug":"sentence-classification-on-scicite","dataset":"SciCite","dataset_url":"/dataset/scicite","rows_in_archive":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"SciBERT","paper_title":"SciBERT: A Pretrained Language Model for Scientific Text","paper_url":"/paper/scibert-pretrained-contextualized-embeddings","paper_date":"2019-03-26","arxiv_id":"1903.10676","code_links":[{"title":"allenai/scibert","url":"https://github.com/allenai/scibert"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"tetsu9923/scireviewgen","url":"https://github.com/tetsu9923/scireviewgen"},{"title":"georgetown-cset/ai-relevant-papers","url":"https://github.com/georgetown-cset/ai-relevant-papers"},{"title":"kuldeep7688/BioMedicalBertNer","url":"https://github.com/kuldeep7688/BioMedicalBertNer"},{"title":"hoangcuongnguyen2001/scibert-for-technique-classification","url":"https://github.com/hoangcuongnguyen2001/scibert-for-technique-classification"}],"syntology":null}},{"leaderboard":"/sota/sentence-classification-on-acl-arc","slug":"sentence-classification-on-acl-arc","dataset":"ACL-ARC","dataset_url":"/dataset/acl-arc-1","rows_in_archive":4,"metrics":["F1"],"first_row_in_archive_order":{"model":"FE-MLM + Span","paper_title":"Improving Self-supervised Pre-training via a Fully-Explored Masked Language Model","paper_url":"/paper/improving-self-supervised-pre-training-via-a-1","paper_date":"2020-10-12","arxiv_id":"2010.06040","code_links":[],"syntology":null}},{"leaderboard":"/sota/sentence-classification-on-paper-field","slug":"sentence-classification-on-paper-field","dataset":"Paper Field","dataset_url":"/dataset/paper-field","rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"SciBERT (SciVocab)","paper_title":"SciBERT: A Pretrained Language Model for Scientific Text","paper_url":"/paper/scibert-pretrained-contextualized-embeddings","paper_date":"2019-03-26","arxiv_id":"1903.10676","code_links":[{"title":"allenai/scibert","url":"https://github.com/allenai/scibert"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"tetsu9923/scireviewgen","url":"https://github.com/tetsu9923/scireviewgen"},{"title":"georgetown-cset/ai-relevant-papers","url":"https://github.com/georgetown-cset/ai-relevant-papers"},{"title":"kuldeep7688/BioMedicalBertNer","url":"https://github.com/kuldeep7688/BioMedicalBertNer"},{"title":"hoangcuongnguyen2001/scibert-for-technique-classification","url":"https://github.com/hoangcuongnguyen2001/scibert-for-technique-classification"}],"syntology":null}},{"leaderboard":"/sota/sentence-classification-on-pubmed-20k-rct","slug":"sentence-classification-on-pubmed-20k-rct","dataset":"PubMed 20k RCT","dataset_url":"/dataset/pubmed","rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"Hierarchical Neural Networks","paper_title":"Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts","paper_url":"/paper/hierarchical-neural-networks-for-sequential","paper_date":"2018-08-19","arxiv_id":"1808.06161","code_links":[{"title":"jind11/HSLN-Joint-Sentence-Classification","url":"https://github.com/jind11/HSLN-Joint-Sentence-Classification"}],"syntology":null}},{"leaderboard":"/sota/sentence-classification-on-sciencecite","slug":"sentence-classification-on-sciencecite","dataset":"ScienceCite","dataset_url":"/dataset/scicite","rows_in_archive":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"SciBERT (SciVocab)","paper_title":"SciBERT: A Pretrained Language Model for Scientific Text","paper_url":"/paper/scibert-pretrained-contextualized-embeddings","paper_date":"2019-03-26","arxiv_id":"1903.10676","code_links":[{"title":"allenai/scibert","url":"https://github.com/allenai/scibert"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"tetsu9923/scireviewgen","url":"https://github.com/tetsu9923/scireviewgen"},{"title":"georgetown-cset/ai-relevant-papers","url":"https://github.com/georgetown-cset/ai-relevant-papers"},{"title":"kuldeep7688/BioMedicalBertNer","url":"https://github.com/kuldeep7688/BioMedicalBertNer"},{"title":"hoangcuongnguyen2001/scibert-for-technique-classification","url":"https://github.com/hoangcuongnguyen2001/scibert-for-technique-classification"}],"syntology":null}},{"leaderboard":"/sota/sentence-classification-on-chip-ctc","slug":"sentence-classification-on-chip-ctc","dataset":"CHIP-CTC","dataset_url":"/dataset/chip-ctc","rows_in_archive":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"RoBERTa-large","paper_title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","paper_url":"/paper/cblue-a-chinese-biomedical-language","paper_date":"2021-06-15","arxiv_id":"2106.08087","code_links":[{"title":"cbluebenchmark/cblue","url":"https://github.com/cbluebenchmark/cblue"},{"title":"freedomintelligence/sdak","url":"https://github.com/freedomintelligence/sdak"}],"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cblue-a-chinese-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/2106.08087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08087"}},"official":{"repos":["cbluebenchmark/cblue"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/pubmed","name":"Pubmed","full_name":"","num_papers_in_archive":1236},{"url":"/dataset/scicite","name":"SciCite","full_name":"SciCite","num_papers_in_archive":40},{"url":"/dataset/pubmed-rct","name":"PubMed RCT","full_name":"PubMed 200k RCT","num_papers_in_archive":20},{"url":"/dataset/acl-arc-1","name":"ACL ARC","full_name":"","num_papers_in_archive":14},{"url":"/dataset/deft-corpus","name":"DEFT Corpus","full_name":"","num_papers_in_archive":14},{"url":"/dataset/indonlu-benchmark","name":"IndoNLU Benchmark","full_name":"","num_papers_in_archive":14},{"url":"/dataset/cspubsum","name":"CSPubSum","full_name":"","num_papers_in_archive":4},{"url":"/dataset/pcmsp","name":"PcMSP","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cards-against-humanity","name":"Cards Against Humanity","full_name":"","num_papers_in_archive":1},{"url":"/dataset/chip-ctc","name":"CHIP-CTC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/csabstrcut-dataset","name":"CSAbstruct Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/e2e-refined","name":"E2E Refined","full_name":"","num_papers_in_archive":1},{"url":"/dataset/paper-field","name":"Paper Field","full_name":"Paper Field","num_papers_in_archive":1},{"url":"/dataset/press-briefing-claim-dataset","name":"Press Briefing Claim Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/unfairness-detection","name":"Unfairness Detection"}],"parent_tasks":[{"url":"/task/text-classification","name":"Text Classification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":303,"of_with_code":115,"tagged_in_all":303,"counts":{"archive_papers_tagged":303,"with_a_code_link":115,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":303,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","repositories_listed":534,"syntology":{"n":659,"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_honours":18,"n_violates":5,"n_no_contract":211,"n_pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}},"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/convolutional-neural-networks-for-sentence","slug":"convolutional-neural-networks-for-sentence","title":"Convolutional Neural Networks for Sentence Classification","date":"2014-08-25","arxiv_id":"1408.5882","repositories_listed":118,"syntology":{"n":77,"n_ran":53,"n_constructed":0,"n_ran_checked":40,"n_instrument":13,"n_unverified":24,"n_honours":6,"n_violates":1,"n_no_contract":33,"n_pointer_only":21,"phrase":"53 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 6 honoured, 1 violated, 33 with no contract checked; 13 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/convolutional-neural-networks-for-sentence#ran","syntology_url":"https://syntology.ai/paper/1408.5882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1408.5882"}},"official":null}},{"url":"/paper/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","repositories_listed":19,"syntology":{"n":25,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}},"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/a-sensitivity-analysis-of-and-practitioners","slug":"a-sensitivity-analysis-of-and-practitioners","title":"A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification","date":"2015-10-13","arxiv_id":"1510.03820","repositories_listed":19,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-sensitivity-analysis-of-and-practitioners#ran","syntology_url":"https://syntology.ai/paper/1510.03820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1510.03820"}},"official":null}},{"url":"/paper/pubmed-200k-rct-a-dataset-for-sequential","slug":"pubmed-200k-rct-a-dataset-for-sequential","title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","date":"2017-10-17","arxiv_id":"1710.06071","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pubmed-200k-rct-a-dataset-for-sequential#ran","syntology_url":"https://syntology.ai/paper/1710.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.06071"}},"official":{"repos":["Franck-Dernoncourt/pubmed-rct"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scibert-pretrained-contextualized-embeddings","slug":"scibert-pretrained-contextualized-embeddings","title":"SciBERT: A Pretrained Language Model for Scientific Text","date":"2019-03-26","arxiv_id":"1903.10676","repositories_listed":6,"syntology":null},{"url":"/paper/what-you-can-cram-into-a-single-vector","slug":"what-you-can-cram-into-a-single-vector","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","date":"2018-05-03","arxiv_id":"1805.01070","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-you-can-cram-into-a-single-vector#ran","syntology_url":"https://syntology.ai/paper/1805.01070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01070"}},"official":{"repos":["facebookresearch/SentEval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-networks-for-joint-sentence","slug":"neural-networks-for-joint-sentence","title":"Neural Networks for Joint Sentence Classification in Medical Paper Abstracts","date":"2016-12-15","arxiv_id":"1612.05251","repositories_listed":5,"syntology":null},{"url":"/paper/rediscovering-hashed-random-projections-for","slug":"rediscovering-hashed-random-projections-for","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","date":"2023-03-13","arxiv_id":"2304.02481","repositories_listed":3,"syntology":null},{"url":"/paper/qnlp-in-practice-running-compositional-models","slug":"qnlp-in-practice-running-compositional-models","title":"QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer","date":"2021-02-25","arxiv_id":"2102.12846","repositories_listed":3,"syntology":null},{"url":"/paper/indonlu-benchmark-and-resources-for","slug":"indonlu-benchmark-and-resources-for","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","date":"2020-09-11","arxiv_id":"2009.05387","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/indonlu-benchmark-and-resources-for#ran","syntology_url":"https://syntology.ai/paper/2009.05387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.05387"}},"official":{"repos":["indobenchmark/indonlu"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/clue-a-chinese-language-understanding","slug":"clue-a-chinese-language-understanding","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","date":"2020-04-13","arxiv_id":"2004.05986","repositories_listed":3,"syntology":null},{"url":"/paper/augmenting-data-with-mixup-for-sentence","slug":"augmenting-data-with-mixup-for-sentence","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","date":"2019-05-22","arxiv_id":"1905.08941","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-data-with-mixup-for-sentence#ran","syntology_url":"https://syntology.ai/paper/1905.08941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08941"}},"official":null}},{"url":"/paper/listops-a-diagnostic-dataset-for-latent-tree","slug":"listops-a-diagnostic-dataset-for-latent-tree","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","date":"2018-04-17","arxiv_id":"1804.06028","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/listops-a-diagnostic-dataset-for-latent-tree#ran","syntology_url":"https://syntology.ai/paper/1804.06028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.06028"}},"official":null}},{"url":"/paper/character-level-and-multi-channel","slug":"character-level-and-multi-channel","title":"Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution","date":"2016-09-21","arxiv_id":"1609.06686","repositories_listed":3,"syntology":null},{"url":"/paper/neural-semantic-encoders","slug":"neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","arxiv_id":"1607.04315","repositories_listed":3,"syntology":null},{"url":"/paper/how-do-large-language-models-learn-in-context","slug":"how-do-large-language-models-learn-in-context","title":"How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning","date":"2024-02-05","arxiv_id":"2402.02872","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-do-large-language-models-learn-in-context#ran","syntology_url":"https://syntology.ai/paper/2402.02872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02872"}},"official":{"repos":["zepingyu0512/in-context-mechanism"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crosslingual-transfer-learning-for-low","slug":"crosslingual-transfer-learning-for-low","title":"Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs","date":"2023-05-22","arxiv_id":"2305.12818","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-tuning-can-be-much-better-than-fine","slug":"prompt-tuning-can-be-much-better-than-fine","title":"Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models","date":"2022-10-22","arxiv_id":"2210.12360","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prompt-tuning-can-be-much-better-than-fine#ran","syntology_url":"https://syntology.ai/paper/2210.12360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12360"}},"official":{"repos":["salesforce/mpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-based-query-strategies-for-active","slug":"uncertainty-based-query-strategies-for-active","title":"Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers","date":"2021-07-12","arxiv_id":"2107.05687","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/uncertainty-based-query-strategies-for-active#ran","syntology_url":"https://syntology.ai/paper/2107.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05687"}},"official":{"repos":["webis-de/acl22-revisiting-uncertainty-based-query-strategies-for-active-learning-with-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cblue-a-chinese-biomedical-language","slug":"cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","arxiv_id":"2106.08087","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cblue-a-chinese-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/2106.08087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08087"}},"official":{"repos":["cbluebenchmark/cblue"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","repositories_listed":2,"syntology":null},{"url":"/paper/voice-srib-at-semeval-2020-task-912-sentiment","slug":"voice-srib-at-semeval-2020-task-912-sentiment","title":"Voice@SRIB at SemEval-2020 Task 9 and 12: Stacked Ensembling method for Sentiment and Offensiveness detection in Social Media","date":"2020-07-20","arxiv_id":"2007.10021","repositories_listed":2,"syntology":null},{"url":"/paper/gan-bert-generative-adversarial-learning-for","slug":"gan-bert-generative-adversarial-learning-for","title":"GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/circe-at-semeval-2020-task-1-ensembling","slug":"circe-at-semeval-2020-task-1-ensembling","title":"CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations","date":"2020-04-30","arxiv_id":"2005.06602","repositories_listed":2,"syntology":null},{"url":"/paper/on-dimensional-linguistic-properties-of-the","slug":"on-dimensional-linguistic-properties-of-the","title":"On Dimensional Linguistic Properties of the Word Embedding Space","date":"2019-10-05","arxiv_id":"1910.02211","repositories_listed":2,"syntology":null},{"url":"/paper/investigating-an-effective-character-level","slug":"investigating-an-effective-character-level","title":"Investigating an Effective Character-level Embedding in Korean Sentence Classification","date":"2019-05-31","arxiv_id":"1905.13656","repositories_listed":2,"syntology":null},{"url":"/paper/a-modular-deep-learning-approach-for-extreme","slug":"a-modular-deep-learning-approach-for-extreme","title":"Taming Pretrained Transformers for Extreme Multi-label Text Classification","date":"2019-05-07","arxiv_id":"1905.02331","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-modular-deep-learning-approach-for-extreme#ran","syntology_url":"https://syntology.ai/paper/1905.02331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02331"}},"official":{"repos":["OctoberChang/X-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/glyce-glyph-vectors-for-chinese-character","slug":"glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","arxiv_id":"1901.10125","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/jointly-learning-to-label-sentences-and","slug":"jointly-learning-to-label-sentences-and","title":"Jointly Learning to Label Sentences and Tokens","date":"2018-11-14","arxiv_id":"1811.05949","repositories_listed":2,"syntology":null},{"url":"/paper/an-attention-gated-convolutional-neural","slug":"an-attention-gated-convolutional-neural","title":"An Attention-Gated Convolutional Neural Network for Sentence Classification","date":"2018-08-22","arxiv_id":"1808.07325","repositories_listed":2,"syntology":null},{"url":"/paper/densely-connected-bidirectional-lstm-with","slug":"densely-connected-bidirectional-lstm-with","title":"Densely Connected Bidirectional LSTM with Applications to Sentence Classification","date":"2018-02-03","arxiv_id":"1802.00889","repositories_listed":2,"syntology":null},{"url":"/paper/a-personalized-conversational-benchmark","slug":"a-personalized-conversational-benchmark","title":"A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations","date":"2025-05-20","arxiv_id":"2505.14106","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-personalized-conversational-benchmark#ran","syntology_url":"https://syntology.ai/paper/2505.14106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14106"}},"official":{"repos":["persona-bench/persona"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tougher-text-smarter-models-raising-the-bar","slug":"tougher-text-smarter-models-raising-the-bar","title":"Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks","date":"2025-01-05","arxiv_id":"2501.02654","repositories_listed":1,"syntology":null},{"url":"/paper/cyber-attack-technique-classification-using","slug":"cyber-attack-technique-classification-using","title":"Cyber-Attack Technique Classification Using Two-Stage Trained Large Language Models","date":"2024-11-27","arxiv_id":"2411.18755","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-sequential-sentence","slug":"multi-label-sequential-sentence","title":"Multi-label Sequential Sentence Classification via Large Language Model","date":"2024-11-23","arxiv_id":"2411.15623","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-anomaly-detection","slug":"large-language-models-for-anomaly-detection","title":"Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning","date":"2024-07-24","arxiv_id":"2407.17545","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-the-level-of-dialectness-predicts","slug":"estimating-the-level-of-dialectness-predicts","title":"Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets","date":"2024-05-18","arxiv_id":"2405.11282","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-guided-fusion-in-decoder","slug":"multi-granularity-guided-fusion-in-decoder","title":"Multi-Granularity Guided Fusion-in-Decoder","date":"2024-04-03","arxiv_id":"2404.02581","repositories_listed":1,"syntology":null},{"url":"/paper/neural-architecture-search-for-sentence","slug":"neural-architecture-search-for-sentence","title":"Neural Architecture Search for Sentence Classification with BERT","date":"2024-03-27","arxiv_id":"2403.18547","repositories_listed":1,"syntology":null},{"url":"/paper/towards-detecting-ai-generated-text-within","slug":"towards-detecting-ai-generated-text-within","title":"Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights","date":"2024-03-06","arxiv_id":"2403.03506","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-detecting-ai-generated-text-within#ran","syntology_url":"https://syntology.ai/paper/2403.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03506"}},"official":{"repos":["douglashiwo/aisentencedetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/can-large-language-models-follow-concept","slug":"can-large-language-models-follow-concept","title":"Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains","date":"2023-11-15","arxiv_id":"2311.08704","repositories_listed":1,"syntology":null},{"url":"/paper/adasent-efficient-domain-adapted-sentence","slug":"adasent-efficient-domain-adapted-sentence","title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","date":"2023-11-01","arxiv_id":"2311.00408","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-sexual-content-at-the-sentence","slug":"detecting-sexual-content-at-the-sentence","title":"Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts","date":"2023-09-25","arxiv_id":"2309.14974","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-to-label-generation-framework-for","slug":"sentence-to-label-generation-framework-for","title":"Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition","date":"2023-06-28","arxiv_id":"2306.15978","repositories_listed":1,"syntology":null},{"url":"/paper/classbases-at-case-2022-multilingual-protest","slug":"classbases-at-case-2022-multilingual-protest","title":"ClassBases at CASE-2022 Multilingual Protest Event Detection Tasks: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets","date":"2023-01-16","arxiv_id":"2301.06617","repositories_listed":1,"syntology":null},{"url":"/paper/disco-distilling-phrasal-counterfactuals-with","slug":"disco-distilling-phrasal-counterfactuals-with","title":"DISCO: Distilling Counterfactuals with Large Language Models","date":"2022-12-20","arxiv_id":"2212.10534","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/disco-distilling-phrasal-counterfactuals-with#ran","syntology_url":"https://syntology.ai/paper/2212.10534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10534"}},"official":{"repos":["eric11eca/disco"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/digicall-a-benchmark-for-measuring-the","slug":"digicall-a-benchmark-for-measuring-the","title":"DigiCall: A Benchmark for Measuring the Maturity of Digital Strategy through Company Earning Calls","date":"2022-12-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/extremebert-a-toolkit-for-accelerating","slug":"extremebert-a-toolkit-for-accelerating","title":"ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT","date":"2022-11-30","arxiv_id":"2211.17201","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/extremebert-a-toolkit-for-accelerating#ran","syntology_url":"https://syntology.ai/paper/2211.17201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.17201"}},"official":{"repos":["extreme-bert/extreme-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gosum-extractive-summarization-of-long","slug":"gosum-extractive-summarization-of-long","title":"GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state","date":"2022-11-18","arxiv_id":"2211.10247","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-infer-from-unlabeled-data-a-semi","slug":"learning-to-infer-from-unlabeled-data-a-semi","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","date":"2022-11-05","arxiv_id":"2211.02971","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-natural-language-generation-on-near","slug":"quantum-natural-language-generation-on-near","title":"Quantum Natural Language Generation on Near-Term Devices","date":"2022-11-01","arxiv_id":"2211.00727","repositories_listed":1,"syntology":null},{"url":"/paper/pcmsp-a-dataset-for-scientific-action-graphs","slug":"pcmsp-a-dataset-for-scientific-action-graphs","title":"PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text","date":"2022-10-22","arxiv_id":"2210.12401","repositories_listed":1,"syntology":null},{"url":"/paper/finding-dataset-shortcuts-with-grammar","slug":"finding-dataset-shortcuts-with-grammar","title":"Finding Dataset Shortcuts with Grammar Induction","date":"2022-10-20","arxiv_id":"2210.11560","repositories_listed":1,"syntology":null},{"url":"/paper/synergy-with-translation-artifacts-for","slug":"synergy-with-translation-artifacts-for","title":"Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks","date":"2022-10-18","arxiv_id":"2210.09588","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/synergy-with-translation-artifacts-for#ran","syntology_url":"https://syntology.ai/paper/2210.09588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09588"}},"official":{"repos":["jongwooko/musc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/making-parameter-efficient-tuning-more","slug":"making-parameter-efficient-tuning-more","title":"Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nsp-bert-a-prompt-based-few-shot-learner","slug":"nsp-bert-a-prompt-based-few-shot-learner","title":"NSP-BERT: A Prompt-based Few-Shot Learner through an Original Pre-training Task —— Next Sentence Prediction","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/query-focused-extractive-summarisation-for-1","slug":"query-focused-extractive-summarisation-for-1","title":"Query-focused Extractive Summarisation for Biomedical and COVID-19 Complex Question Answering","date":"2022-09-05","arxiv_id":"2209.01815","repositories_listed":1,"syntology":null},{"url":"/paper/attentionsitedti-an-interpretable-graph-based","slug":"attentionsitedti-an-interpretable-graph-based","title":"AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification","date":"2022-07-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/placing-historical-facts-on-a-timeline-a","slug":"placing-historical-facts-on-a-timeline-a","title":"Placing (Historical) Facts on a Timeline: A Classification cum Coref Resolution Approach","date":"2022-06-28","arxiv_id":"2206.14089","repositories_listed":1,"syntology":null},{"url":"/paper/synwmd-syntax-aware-word-mover-s-distance-for","slug":"synwmd-syntax-aware-word-mover-s-distance-for","title":"SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation","date":"2022-06-20","arxiv_id":"2206.10029","repositories_listed":1,"syntology":null},{"url":"/paper/composing-structure-aware-batches-for-1","slug":"composing-structure-aware-batches-for-1","title":"Composing Structure-Aware Batches for Pairwise Sentence Classification","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dmix-adaptive-distance-aware-interpolative","slug":"dmix-adaptive-distance-aware-interpolative","title":"DMix: Adaptive Distance-aware Interpolative Mixup","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/datamux-data-multiplexing-for-neural-networks","slug":"datamux-data-multiplexing-for-neural-networks","title":"DataMUX: Data Multiplexing for Neural Networks","date":"2022-02-18","arxiv_id":"2202.09318","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":3,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/datamux-data-multiplexing-for-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2202.09318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09318"}},"official":{"repos":["princeton-nlp/datamux"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploiting-all-samples-in-low-resource","slug":"exploiting-all-samples-in-low-resource","title":"Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters","date":"2021-11-12","arxiv_id":"2111.06971","repositories_listed":1,"syntology":null},{"url":"/paper/causal-augmentation-for-causal-sentence","slug":"causal-augmentation-for-causal-sentence","title":"Causal Augmentation for Causal Sentence Classification","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evidence-selection-as-a-token-level","slug":"evidence-selection-as-a-token-level","title":"Evidence Selection as a Token-Level Prediction Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/contextual-sentence-classification-detecting","slug":"contextual-sentence-classification-detecting","title":"Contextual Sentence Classification: Detecting Sustainability Initiatives in Company Reports","date":"2021-10-07","arxiv_id":"2110.03727","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-self-training-for-few-shot","slug":"revisiting-self-training-for-few-shot","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","date":"2021-10-04","arxiv_id":"2110.01256","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/revisiting-self-training-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2110.01256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01256"}},"official":{"repos":["matthewcym/sflm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/mdapt-multilingual-domain-adaptive","slug":"mdapt-multilingual-domain-adaptive","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","date":"2021-09-14","arxiv_id":"2109.06605","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-adversarial-learning-with","slug":"counterfactual-adversarial-learning-with","title":"Counterfactual Adversarial Learning with Representation Interpolation","date":"2021-09-10","arxiv_id":"2109.04746","repositories_listed":1,"syntology":null},{"url":"/paper/tree-constrained-graph-neural-networks-for","slug":"tree-constrained-graph-neural-networks-for","title":"Tree-Constrained Graph Neural Networks For Argument Mining","date":"2021-09-02","arxiv_id":"2110.00124","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-bottleneck-autoencoders-from","slug":"sentence-bottleneck-autoencoders-from","title":"Sentence Bottleneck Autoencoders from Transformer Language Models","date":"2021-08-31","arxiv_id":"2109.00055","repositories_listed":1,"syntology":null},{"url":"/paper/query-focused-extractive-summarisation-for","slug":"query-focused-extractive-summarisation-for","title":"Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions","date":"2021-08-27","arxiv_id":"2108.12189","repositories_listed":1,"syntology":null},{"url":"/paper/textcnn-with-attention-for-text","slug":"textcnn-with-attention-for-text","title":"TextCNN with Attention for Text Classification","date":"2021-08-04","arxiv_id":"2108.01921","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-human-reading-comprehension","slug":"understanding-human-reading-comprehension","title":"Towards a Better Understanding Human Reading Comprehension with Brain Signals","date":"2021-08-03","arxiv_id":"2108.01360","repositories_listed":1,"syntology":null},{"url":"/paper/entity-at-semeval-2021-task-5-weakly","slug":"entity-at-semeval-2021-task-5-weakly","title":"Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iiitt-at-case-2021-task-1-leveraging","slug":"iiitt-at-case-2021-task-1-leveraging","title":"IIITT at CASE 2021 Task 1: Leveraging Pretrained Language Models for Multilingual Protest Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uiuc-bionlp-at-semeval-2021-task-11-a-cascade-1","slug":"uiuc-bionlp-at-semeval-2021-task-11-a-cascade-1","title":"UIUC\\_BioNLP at SemEval-2021 Task 11: A Cascade of Neural Models for Structuring Scholarly NLP Contributions","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/corpus-level-evaluation-for-event-qa-the","slug":"corpus-level-evaluation-for-event-qa-the","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","date":"2021-05-27","arxiv_id":"2105.12936","repositories_listed":1,"syntology":null},{"url":"/paper/uiuc-bionlp-at-semeval-2021-task-11-a-cascade","slug":"uiuc-bionlp-at-semeval-2021-task-11-a-cascade","title":"UIUC_BioNLP at SemEval-2021 Task 11: A Cascade of Neural Models for Structuring Scholarly NLP Contributions","date":"2021-05-12","arxiv_id":"2105.05435","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-sentence-classification-in","slug":"sequential-sentence-classification-in","title":"Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Papers","date":"2021-02-11","arxiv_id":"2102.06008","repositories_listed":1,"syntology":null},{"url":"/paper/banglabert-combating-embedding-barrier-for","slug":"banglabert-combating-embedding-barrier-for","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","date":"2021-01-01","arxiv_id":"2101.00204","repositories_listed":1,"syntology":null},{"url":"/paper/improving-bert-with-syntax-aware-local","slug":"improving-bert-with-syntax-aware-local","title":"Improving BERT with Syntax-aware Local Attention","date":"2020-12-30","arxiv_id":"2012.15150","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-learning-of-feature-based-meta","slug":"adversarial-learning-of-feature-based-meta","title":"FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations","date":"2020-10-23","arxiv_id":"2010.12305","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-word-sense-disambiguation-in","slug":"multimodal-word-sense-disambiguation-in","title":"Multimodal Word Sense Disambiguation in Creative Practice","date":"2020-07-15","arxiv_id":"2007.07758","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-latent-variable-representations-for","slug":"discrete-latent-variable-representations-for","title":"Discrete Latent Variable Representations for Low-Resource Text Classification","date":"2020-06-11","arxiv_id":"2006.06226","repositories_listed":1,"syntology":null},{"url":"/paper/posterior-calibrated-training-on-sentence","slug":"posterior-calibrated-training-on-sentence","title":"Posterior Calibrated Training on Sentence Classification Tasks","date":"2020-04-29","arxiv_id":"2004.14500","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","repositories_listed":1,"syntology":null},{"url":"/paper/the-russian-drug-reaction-corpus-and-neural","slug":"the-russian-drug-reaction-corpus-and-neural","title":"The Russian Drug Reaction Corpus and Neural Models for Drug Reactions and Effectiveness Detection in User Reviews","date":"2020-04-07","arxiv_id":"2004.03659","repositories_listed":1,"syntology":null},{"url":"/paper/cost-sensitive-bert-for-generalisable-1","slug":"cost-sensitive-bert-for-generalisable-1","title":"Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data","date":"2020-03-16","arxiv_id":"2003.11563","repositories_listed":1,"syntology":null},{"url":"/paper/neural-simile-recognition-with-cyclic","slug":"neural-simile-recognition-with-cyclic","title":"Neural Simile Recognition with Cyclic Multitask Learning and Local Attention","date":"2019-12-19","arxiv_id":"1912.09084","repositories_listed":1,"syntology":null},{"url":"/paper/pyss3-a-python-package-implementing-a-novel","slug":"pyss3-a-python-package-implementing-a-novel","title":"PySS3: A Python package implementing a novel text classifier with visualization tools for Explainable AI","date":"2019-12-19","arxiv_id":"1912.09322","repositories_listed":1,"syntology":null},{"url":"/paper/t-ss3-a-text-classifier-with-dynamic-n-grams","slug":"t-ss3-a-text-classifier-with-dynamic-n-grams","title":"t-SS3: a text classifier with dynamic n-grams for early risk detection over text streams","date":"2019-11-11","arxiv_id":"1911.06147","repositories_listed":1,"syntology":null},{"url":"/paper/a-joint-model-for-definition-extraction-with","slug":"a-joint-model-for-definition-extraction-with","title":"A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency","date":"2019-11-05","arxiv_id":"1911.01678","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-via-membership-query","slug":"active-learning-via-membership-query","title":"Active Learning via Membership Query Synthesis for Semi-Supervised Sentence Classification","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-language-models-for-sequential","slug":"pretrained-language-models-for-sequential","title":"Pretrained Language Models for Sequential Sentence Classification","date":"2019-09-09","arxiv_id":"1909.04054","repositories_listed":1,"syntology":null},{"url":"/paper/bivariate-beta-lstm","slug":"bivariate-beta-lstm","title":"Bivariate Beta-LSTM","date":"2019-05-25","arxiv_id":"1905.10521","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bivariate-beta-lstm#ran","syntology_url":"https://syntology.ai/paper/1905.10521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10521"}},"official":{"repos":["gtshs2/BetaLSTM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/190602127","slug":"190602127","title":"An Approach for Process Model Extraction By Multi-Grained Text Classification","date":"2019-05-16","arxiv_id":"1906.02127","repositories_listed":1,"syntology":null}],"syntology_records":23,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/task/sentence-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/sentence-classification/papers/2","json":"/task/sentence-classification/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/sentence-classification/papers/3","json":"/task/sentence-classification/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/sentence-classification/papers/4","json":"/task/sentence-classification/papers/4.json","rows":3},{"order":"ran","page":1,"of":1,"url":"/task/sentence-classification/papers/ran/1","json":"/task/sentence-classification/papers/ran/1.json","rows":22}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a7c1b6d2601e837d2eefcf28e8247b0f40234bc00e85fff416698673ffcc7d78","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}