{"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/keyword-extraction","name":"Keyword Extraction","slug":"keyword-extraction","description_markdown":"Keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document (Source: Wikipedia).","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":172,"papers_with_code":33,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/keyword-extraction-on-inspec","slug":"keyword-extraction-on-inspec","dataset":"Inspec","dataset_url":"/dataset/inspec","rows_in_archive":5,"metrics":["F1 score","Precision@10","Recall @ 10"],"first_row_in_archive_order":{"model":"Phraseformer(BERT, ExEm(ft))","paper_title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","paper_url":"/paper/phraseformer-multimodal-key-phrase-extraction","paper_date":"2021-06-09","arxiv_id":"2106.04939","code_links":[],"syntology":null}},{"leaderboard":"/sota/keyword-extraction-on-semeval-2010-task-8","slug":"keyword-extraction-on-semeval-2010-task-8","dataset":"SemEval 2010 Task 8","dataset_url":null,"rows_in_archive":5,"metrics":["F1 score","Precision@10","Recall@10"],"first_row_in_archive_order":{"model":"Phraseformer(BERT, ExEm(ft))","paper_title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","paper_url":"/paper/phraseformer-multimodal-key-phrase-extraction","paper_date":"2021-06-09","arxiv_id":"2106.04939","code_links":[],"syntology":null}},{"leaderboard":"/sota/keyword-extraction-on-semeval2017","slug":"keyword-extraction-on-semeval2017","dataset":"SemEval-2017 Task-10","dataset_url":"/dataset/semeval2017","rows_in_archive":5,"metrics":["F1 score","Precision@10","Recall@10"],"first_row_in_archive_order":{"model":"Phraseformer(BERT, ExEm(ft))","paper_title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","paper_url":"/paper/phraseformer-multimodal-key-phrase-extraction","paper_date":"2021-06-09","arxiv_id":"2106.04939","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/mpqa-opinion-corpus","name":"MPQA Opinion Corpus","full_name":"Multi-Perspective Question Answering","num_papers_in_archive":313},{"url":"/dataset/semeval2017","name":"SemEval-2017 Task-10","full_name":"","num_papers_in_archive":33},{"url":"/dataset/kptimes","name":"KPTimes","full_name":"","num_papers_in_archive":27},{"url":"/dataset/inspec","name":"Inspec","full_name":"","num_papers_in_archive":7},{"url":"/dataset/csl-2022","name":"CSL (Chinese Scientific Literature)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/keyphrases-cs-math-russian","name":"Keyphrases CS&Math Russian","full_name":"Keyphrases CS&Math Russian","num_papers_in_archive":1},{"url":"/dataset/maked","name":"MAKED","full_name":"MultiModal MultiLingual Summarization and Keyword Extraction Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":2,"rows_per_page":100,"shown":100,"of":172,"of_with_code":33,"tagged_in_all":172,"counts":{"archive_papers_tagged":172,"with_a_code_link":33,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":172,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/181110831","slug":"181110831","title":"sCAKE: Semantic Connectivity Aware Keyword Extraction","date":"2018-11-27","arxiv_id":"1811.10831","repositories_listed":5,"syntology":null},{"url":"/paper/complex-network-based-supervised-keyword","slug":"complex-network-based-supervised-keyword","title":"Complex Network based Supervised Keyword Extractor","date":"2019-09-26","arxiv_id":"1909.12009","repositories_listed":2,"syntology":null},{"url":"/paper/pscon-toward-conversational-product-search","slug":"pscon-toward-conversational-product-search","title":"PSCon: Product Search Through Conversations","date":"2025-02-19","arxiv_id":"2502.13881","repositories_listed":1,"syntology":null},{"url":"/paper/seke-specialised-experts-for-keyword","slug":"seke-specialised-experts-for-keyword","title":"SEKE: Specialised Experts for Keyword Extraction","date":"2024-12-18","arxiv_id":"2412.14087","repositories_listed":1,"syntology":null},{"url":"/paper/llms-are-biased-evaluators-but-not-biased-for","slug":"llms-are-biased-evaluators-but-not-biased-for","title":"LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation","date":"2024-10-28","arxiv_id":"2410.20833","repositories_listed":1,"syntology":null},{"url":"/paper/robust-privacy-amidst-innovation-with-large","slug":"robust-privacy-amidst-innovation-with-large","title":"Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks","date":"2024-07-23","arxiv_id":"2407.16166","repositories_listed":1,"syntology":null},{"url":"/paper/an-improved-method-for-class-specific-keyword","slug":"an-improved-method-for-class-specific-keyword","title":"An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry","date":"2024-07-19","arxiv_id":"2407.14085","repositories_listed":1,"syntology":null},{"url":"/paper/anytasktune-advanced-domain-specific","slug":"anytasktune-advanced-domain-specific","title":"AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning","date":"2024-07-09","arxiv_id":"2407.07094","repositories_listed":1,"syntology":null},{"url":"/paper/open-world-multi-label-text-classification","slug":"open-world-multi-label-text-classification","title":"Open-world Multi-label Text Classification with Extremely Weak Supervision","date":"2024-07-08","arxiv_id":"2407.05609","repositories_listed":1,"syntology":null},{"url":"/paper/ksw-khmer-stop-word-based-dictionary-for","slug":"ksw-khmer-stop-word-based-dictionary-for","title":"KSW: Khmer Stop Word based Dictionary for Keyword Extraction","date":"2024-05-27","arxiv_id":"2405.17390","repositories_listed":1,"syntology":null},{"url":"/paper/speechclip-self-supervised-multi-task","slug":"speechclip-self-supervised-multi-task","title":"SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data","date":"2024-02-10","arxiv_id":"2402.06959","repositories_listed":1,"syntology":null},{"url":"/paper/task-oriented-conversational-modelling-with","slug":"task-oriented-conversational-modelling-with","title":"Task Oriented Conversational Modelling With Subjective Knowledge","date":"2023-03-30","arxiv_id":"2303.17695","repositories_listed":1,"syntology":null},{"url":"/paper/graph-based-semantical-extractive-text","slug":"graph-based-semantical-extractive-text","title":"Graph-based Semantical Extractive Text Analysis","date":"2022-12-19","arxiv_id":"2212.09701","repositories_listed":1,"syntology":null},{"url":"/paper/adaptkeybert-an-attention-based-approach","slug":"adaptkeybert-an-attention-based-approach","title":"AdaptKeyBERT: An Attention-Based approach towards Few-Shot & Zero-Shot Domain Adaptation of KeyBERT","date":"2022-11-14","arxiv_id":"2211.07499","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-bidirectional-training-for-zero","slug":"large-scale-bidirectional-training-for-zero","title":"Large-Scale Bidirectional Training for Zero-Shot Image Captioning","date":"2022-11-13","arxiv_id":"2211.06774","repositories_listed":1,"syntology":null},{"url":"/paper/sidi-kws-a-large-scale-multilingual-dataset","slug":"sidi-kws-a-large-scale-multilingual-dataset","title":"SiDi KWS: A Large-Scale Multilingual Dataset for Keyword Spotting","date":"2022-09-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/study-of-keyword-extraction-techniques-for","slug":"study-of-keyword-extraction-techniques-for","title":"Study of keyword extraction techniques for Electric Double Layer Capacitor domain using text similarity indexes: An experimental analysis","date":"2021-11-13","arxiv_id":"2111.07068","repositories_listed":1,"syntology":null},{"url":"/paper/mderank-a-masked-document-embedding-rank","slug":"mderank-a-masked-document-embedding-rank","title":"MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction","date":"2021-10-13","arxiv_id":"2110.06651","repositories_listed":1,"syntology":null},{"url":"/paper/drift-a-toolkit-for-diachronic-analysis-of","slug":"drift-a-toolkit-for-diachronic-analysis-of","title":"DRIFT: A Toolkit for Diachronic Analysis of Scientific Literature","date":"2021-07-02","arxiv_id":"2107.01198","repositories_listed":1,"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/drift-a-toolkit-for-diachronic-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2107.01198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01198"}},"official":{"repos":["rajaswa/DRIFT"],"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":["found_in_text"]}}},{"url":"/paper/back-to-the-basics-a-quantitative-analysis-of","slug":"back-to-the-basics-a-quantitative-analysis-of","title":"Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction","date":"2021-04-16","arxiv_id":"2104.08028","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/back-to-the-basics-a-quantitative-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2104.08028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08028"}},"official":{"repos":["asahi417/kex"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/frake-fusional-real-time-automatic-keyword","slug":"frake-fusional-real-time-automatic-keyword","title":"FRAKE: Fusional Real-time Automatic Keyword Extraction","date":"2021-04-10","arxiv_id":"2104.04830","repositories_listed":1,"syntology":null},{"url":"/paper/elske-efficient-large-scale-keyphrase","slug":"elske-efficient-large-scale-keyphrase","title":"ELSKE: Efficient Large-Scale Keyphrase Extraction","date":"2021-02-10","arxiv_id":"2102.05700","repositories_listed":1,"syntology":null},{"url":"/paper/extending-neural-keyword-extraction-with-tf","slug":"extending-neural-keyword-extraction-with-tf","title":"Extending Neural Keyword Extraction with TF-IDF tagset matching","date":"2021-01-31","arxiv_id":"2102.00472","repositories_listed":1,"syntology":null},{"url":"/paper/outline-to-story-fine-grained-controllable","slug":"outline-to-story-fine-grained-controllable","title":"Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events","date":"2021-01-04","arxiv_id":"2101.00822","repositories_listed":1,"syntology":null},{"url":"/paper/literature-retrieval-for-precision-medicine","slug":"literature-retrieval-for-precision-medicine","title":"Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization","date":"2020-12-17","arxiv_id":"2012.09355","repositories_listed":1,"syntology":null},{"url":"/paper/keywords-lie-far-from-the-mean-of-all-words","slug":"keywords-lie-far-from-the-mean-of-all-words","title":"Keywords lie far from the mean of all words in local vector space","date":"2020-08-21","arxiv_id":"2008.09513","repositories_listed":1,"syntology":null},{"url":"/paper/tnt-kid-transformer-based-neural-tagger-for","slug":"tnt-kid-transformer-based-neural-tagger-for","title":"TNT-KID: Transformer-based Neural Tagger for Keyword Identification","date":"2020-03-20","arxiv_id":"2003.09166","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-sensitive-tf-idf-to-determine-word","slug":"semantic-sensitive-tf-idf-to-determine-word","title":"Semantic Sensitive TF-IDF to Determine Word Relevance in Documents","date":"2020-01-06","arxiv_id":"2001.09896","repositories_listed":1,"syntology":null},{"url":"/paper/rakun-rank-based-keyword-extraction-via","slug":"rakun-rank-based-keyword-extraction-via","title":"RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation","date":"2019-07-15","arxiv_id":"1907.06458","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-generation-and-processing-of-word","slug":"efficient-generation-and-processing-of-word","title":"Efficient Generation and Processing of Word Co-occurrence Networks Using corpus2graph","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/yake-keyword-extraction-from-single-documents","slug":"yake-keyword-extraction-from-single-documents","title":"YAKE! Keyword extraction from single documents using multiple local features","date":"2018-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/combining-graph-degeneracy-and-submodularity","slug":"combining-graph-degeneracy-and-submodularity","title":"Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-graph-degeneracy-based-approach-to-keyword","slug":"a-graph-degeneracy-based-approach-to-keyword","title":"A Graph Degeneracy-based Approach to Keyword Extraction","date":"2016-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"cost-efficient-serving-of-llm-agents-via-test","title":"Cost-Efficient Serving of LLM Agents via Test-Time Plan Caching","date":"2025-06-17","arxiv_id":"2506.14852","repositories_listed":0,"syntology":null},{"url":null,"slug":"urania-differentially-private-insights-into","title":"Urania: Differentially Private Insights into AI Use","date":"2025-06-05","arxiv_id":"2506.04681","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-precision-to-perception-user-centred","title":"From Precision to Perception: User-Centred Evaluation of Keyword Extraction Algorithms for Internet-Scale Contextual Advertising","date":"2025-04-30","arxiv_id":"2504.21667","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-extraction-and-aspect-classification","title":"Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content","date":"2025-04-14","arxiv_id":"2504.10679","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-chatgpt-for-sponsored-ad-detection","title":"Leveraging ChatGPT for Sponsored Ad Detection and Keyword Extraction in YouTube Videos","date":"2025-02-20","arxiv_id":"2502.15102","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-a-good-caption-a-comprehensive-visual","title":"What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","date":"2025-02-19","arxiv_id":"2502.14914","repositories_listed":0,"syntology":null},{"url":null,"slug":"approach-to-visual-attractiveness-of-event","title":"Approach to Visual Attractiveness of Event Space Through Data-Driven Environment and Spatial Perception","date":"2025-01-20","arxiv_id":"2503.15499","repositories_listed":0,"syntology":null},{"url":null,"slug":"gptdrawer-enhancing-visual-synthesis-through","title":"GPTDrawer: Enhancing Visual Synthesis through ChatGPT","date":"2024-12-11","arxiv_id":"2412.10429","repositories_listed":0,"syntology":null},{"url":null,"slug":"evqascore-efficient-video-question-answering","title":"EVQAScore: Efficient Video Question Answering Data Evaluation","date":"2024-11-11","arxiv_id":"2411.06908","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-rigour-of-scientific-writing-criteria","title":"On the Rigour of Scientific Writing: Criteria, Analysis, and Insights","date":"2024-10-07","arxiv_id":"2410.04981","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-keyword-extraction-with-keyness","title":"Cross-Domain Keyword Extraction with Keyness Patterns","date":"2024-09-27","arxiv_id":"2409.18724","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-generation-of-web-censorship-probe","title":"Automatic Generation of Web Censorship Probe Lists","date":"2024-07-11","arxiv_id":"2407.08185","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-prompt-words-learning-for-social","title":"Multi-task Prompt Words Learning for Social Media Content Generation","date":"2024-07-10","arxiv_id":"2407.07771","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-method-for-keyword-extraction-for-patent","title":"New Method for Keyword Extraction for Patent Claims","date":"2024-07-08","arxiv_id":"2407.07923","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enhanced-clustering-for","title":"Large Language Model Enhanced Clustering for News Event Detection","date":"2024-06-15","arxiv_id":"2406.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-document-based-knowledge-discovery-with","title":"A Document-based Knowledge Discovery with Microservices Architecture","date":"2024-06-13","arxiv_id":"2407.00053","repositories_listed":0,"syntology":null},{"url":null,"slug":"khmer-semantic-search-engine-digital","title":"Khmer Semantic Search Engine (KSE): Digital Information Access and Document Retrieval","date":"2024-06-13","arxiv_id":"2406.09320","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-traffic-crash-narratives-in-jordan","title":"Exploring Traffic Crash Narratives in Jordan Using Text Mining Analytics","date":"2024-06-11","arxiv_id":"2406.09438","repositories_listed":0,"syntology":null},{"url":null,"slug":"thesis-document-summarization-with","title":"Thesis: Document Summarization with applications to Keyword extraction and Image Retrieval","date":"2024-05-20","arxiv_id":"2406.00013","repositories_listed":0,"syntology":null},{"url":null,"slug":"perkwe-coqa-enhance-persian-conversational","title":"PerkwE_COQA: Enhanced Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models","date":"2024-04-08","arxiv_id":"2404.05406","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-study-of-domain-driven-terms","title":"Comparative Study of Domain Driven Terms Extraction Using Large Language Models","date":"2024-04-02","arxiv_id":"2404.02330","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-persian-news-agencies-on","title":"Analysis of Persian News Agencies on Instagram, A Words Co-occurrence Graph-based Approach","date":"2024-02-19","arxiv_id":"2402.12272","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-zero-shot-prompting-in-the-automatic","title":"Using Zero-shot Prompting in the Automatic Creation and Expansion of Topic Taxonomies for Tagging Retail Banking Transactions","date":"2024-01-08","arxiv_id":"2401.06790","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-take-theme-aware-keyword-extraction-using","title":"LLM-TAKE: Theme Aware Keyword Extraction Using Large Language Models","date":"2023-12-01","arxiv_id":"2312.00909","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-annotation-of-scientific-texts-for","title":"Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation","date":"2023-11-08","arxiv_id":"2311.05042","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cloud-based-machine-learning-pipeline-for","title":"A Cloud-based Machine Learning Pipeline for the Efficient Extraction of Insights from Customer Reviews","date":"2023-06-13","arxiv_id":"2306.07786","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-not-quote-out-of-context-unified-vision","title":"\"Let's not Quote out of Context\": Unified Vision-Language Pretraining for Context Assisted Image Captioning","date":"2023-06-01","arxiv_id":"2306.00931","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-the-locations-and-predicting-future","title":"Ranking the locations and predicting future crime occurrence by retrieving news from different Bangla online newspapers","date":"2023-05-18","arxiv_id":"2305.10698","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-processing-on-customer-note","title":"Natural language processing on customer note data","date":"2023-05-03","arxiv_id":"2305.02029","repositories_listed":0,"syntology":null},{"url":null,"slug":"thematic-context-vector-association-based-on","title":"Thematic context vector association based on event uncertainty for Twitter","date":"2023-04-04","arxiv_id":"2304.01423","repositories_listed":0,"syntology":null},{"url":null,"slug":"jobham-place-with-smart-recommend-job-options","title":"JobHam-place with smart recommend job options and candidate filtering options","date":"2023-03-31","arxiv_id":"2303.17930","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-method-for-incremental-discovery-of","title":"A method for incremental discovery of financial event types based on anomaly detection","date":"2023-02-16","arxiv_id":"2302.08205","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-embedding-neural-networks-to-advance","title":"Word Embedding Neural Networks to Advance Knee Osteoarthritis Research","date":"2022-12-22","arxiv_id":"2212.11933","repositories_listed":0,"syntology":null},{"url":null,"slug":"norm-of-word-embedding-encodes-information","title":"Norm of Word Embedding Encodes Information Gain","date":"2022-12-19","arxiv_id":"2212.09663","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-performance-of-automatic-keyword","title":"Improving Performance of Automatic Keyword Extraction (AKE) Methods Using PoS-Tagging and Enhanced Semantic-Awareness","date":"2022-11-09","arxiv_id":"2211.05031","repositories_listed":0,"syntology":null},{"url":null,"slug":"reusing-keywords-for-fine-grained","title":"Multi-view Semantic Matching of Question retrieval using Fine-grained Semantic Representations","date":"2022-10-21","arxiv_id":"2210.11806","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-based-natural-language-premise","title":"Keyword-based Natural Language Premise Selection for an Automatic Mathematical Statement Proving","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-and-cross-view-brain-decoding","title":"Multi-view and Cross-view Brain Decoding","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zhuan-ye-ji-zhu-wen-ben-guan-jian-ci-chou-qu","title":"专业技术文本关键词抽取方法(Keyword Extraction on Professional Technical Text)","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-extraction-from-short-texts-with-a","title":"Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer","date":"2022-09-28","arxiv_id":"2209.14008","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-job-interview-system-using","title":"Simultaneous Job Interview System Using Multiple Semi-autonomous Agents","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-efficiency-trade-off-of","title":"Retrieval-efficiency trade-off of Unsupervised Keyword Extraction","date":"2022-08-15","arxiv_id":"2208.07262","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimib-at-trec-2021-clinical-trials-track","title":"UNIMIB at TREC 2021 Clinical Trials Track","date":"2022-07-27","arxiv_id":"2207.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-extraction-in-scientific-documents","title":"Keyword Extraction in Scientific Documents","date":"2022-07-05","arxiv_id":"2207.01888","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-algorithms-for-keyword","title":"Unsupervised Learning Algorithms for Keyword Extraction in an Undergraduate Thesis","date":"2022-06-23","arxiv_id":"2206.12016","repositories_listed":0,"syntology":null},{"url":null,"slug":"born-for-auto-tagging-faster-and-better-with","title":"Born for Auto-Tagging: Faster and better with new objective functions","date":"2022-06-15","arxiv_id":"2206.07264","repositories_listed":0,"syntology":null},{"url":null,"slug":"embeddia-project-cross-lingual-embeddings-for","title":"EMBEDDIA project: Cross-Lingual Embeddings for Less- Represented Languages in European News Media","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/maked-multi-lingual-automatic-keyword","slug":"maked-multi-lingual-automatic-keyword","title":"MAKED: Multi-lingual Automatic Keyword Extraction Dataset","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-virtual-edges-to-extract-keywords-from","title":"Using virtual edges to extract keywords from texts modeled as complex networks","date":"2022-05-04","arxiv_id":"2205.02172","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-view-brain-decoding","title":"Cross-view Brain Decoding","date":"2022-04-18","arxiv_id":"2204.09564","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-similarity-computing-for-scientific","title":"Semantic Similarity Computing for Scientific Academic Conferences fused with domain features","date":"2022-03-21","arxiv_id":"2203.12593","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-thin-air-is-zero-shot-cross-lingual","title":"Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?","date":"2022-02-14","arxiv_id":"2202.06650","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-domain-response-generation-guided-by","title":"Open Domain Response Generation Guided by Retrieved Conversations","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coherence-based-document-clustering","title":"Coherence-Based Document Clustering","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-point-based-document","title":"Explainable Point-Based Document Visualizations","date":"2021-09-28","arxiv_id":"2110.00462","repositories_listed":0,"syntology":null},{"url":null,"slug":"solar-cell-patent-classification-method-based","title":"Solar cell patent classification method based on keyword extraction and deep neural network","date":"2021-09-18","arxiv_id":"2109.08796","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-extraction-for-improved-document","title":"Keyword Extraction for Improved Document Retrieval in Conversational Search","date":"2021-09-13","arxiv_id":"2109.05979","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-learning-on-keywords-for","title":"Sequence-to-Sequence Learning on Keywords for Efficient FAQ Retrieval","date":"2021-08-23","arxiv_id":"2108.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualtextrank-unsupervised-graph-based","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","date":"2021-08-05","arxiv_id":"2108.02725","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmpose-nlp-a-natural-language-processing","title":"mmPose-NLP: A Natural Language Processing Approach to Precise Skeletal Pose Estimation using mmWave Radars","date":"2021-07-21","arxiv_id":"2107.10327","repositories_listed":0,"syntology":null},{"url":"/paper/phraseformer-multimodal-key-phrase-extraction","slug":"phraseformer-multimodal-key-phrase-extraction","title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","date":"2021-06-09","arxiv_id":"2106.04939","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-extraction-using-unsupervised","title":"Keyword Extraction Using Unsupervised Learning on the Document’s Adjacency Matrix","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-linguistically-lightweight-keyword","title":"Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gepsa-a-tool-for-monitoring-social-challenges","title":"GEPSA, a tool for monitoring social challenges in digital press","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-sentence-similarity-for-sms-dataset","title":"On-Device Sentence Similarity for SMS Dataset","date":"2020-12-04","arxiv_id":"2012.02819","repositories_listed":0,"syntology":null},{"url":null,"slug":"n-grams-textrank-a-novel-domain-keyword","title":"N-Grams TextRank A Novel Domain Keyword Extraction Technique","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-recognition-and-relation-extraction","title":"Entity Recognition and Relation Extraction from Scientific and Technical Texts in Russian","date":"2020-11-19","arxiv_id":"2011.09817","repositories_listed":0,"syntology":null}],"syntology_records":2,"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":2,"papers_where_code_ran_first_page":"/task/keyword-extraction/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":2,"url":"/task/keyword-extraction/papers/2","json":"/task/keyword-extraction/papers/2.json","rows":72},{"order":"ran","page":1,"of":1,"url":"/task/keyword-extraction/papers/ran/1","json":"/task/keyword-extraction/papers/ran/1.json","rows":2}],"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":"e7de6061040a691443e657bba4494f32a54dc1d76fc845d0f644587497692988","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}