{"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/de-en","name":"de-en","slug":"de-en","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":82,"papers_with_code":33,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/cvss","name":"CVSS","full_name":"","num_papers_in_archive":26}],"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":1,"rows_per_page":100,"shown":82,"of":82,"of_with_code":33,"tagged_in_all":82,"counts":{"archive_papers_tagged":82,"with_a_code_link":33,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":82,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/wide-minima-density-hypothesis-and-the","slug":"wide-minima-density-hypothesis-and-the","title":"Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule","date":"2020-03-09","arxiv_id":"2003.03977","repositories_listed":5,"syntology":null},{"url":"/paper/batchensemble-an-alternative-approach-to-1","slug":"batchensemble-an-alternative-approach-to-1","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","date":"2020-02-17","arxiv_id":"2002.06715","repositories_listed":5,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/batchensemble-an-alternative-approach-to-1#ran","syntology_url":"https://syntology.ai/paper/2002.06715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06715"}},"official":{"repos":["google/edward2"],"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/stacl-simultaneous-translation-with","slug":"stacl-simultaneous-translation-with","title":"STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework","date":"2018-10-19","arxiv_id":"1810.08398","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stacl-simultaneous-translation-with#ran","syntology_url":"https://syntology.ai/paper/1810.08398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.08398"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"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/bert-mbert-or-bibert-a-study-on","slug":"bert-mbert-or-bibert-a-study-on","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","date":"2021-09-09","arxiv_id":"2109.04588","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bert-mbert-or-bibert-a-study-on#ran","syntology_url":"https://syntology.ai/paper/2109.04588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04588"}},"official":{"repos":["fe1ixxu/BiBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fully-character-level-neural-machine","slug":"fully-character-level-neural-machine","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","date":"2016-10-10","arxiv_id":"1610.03017","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fully-character-level-neural-machine#ran","syntology_url":"https://syntology.ai/paper/1610.03017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.03017"}},"official":{"repos":["nyu-dl/dl4mt-c2c"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-character-level-decoder-without-explicit","slug":"a-character-level-decoder-without-explicit","title":"A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation","date":"2016-03-19","arxiv_id":"1603.06147","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-character-level-decoder-without-explicit#ran","syntology_url":"https://syntology.ai/paper/1603.06147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.06147"}},"official":null}},{"url":"/paper/streamspeech-simultaneous-speech-to-speech","slug":"streamspeech-simultaneous-speech-to-speech","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","date":"2024-06-05","arxiv_id":"2406.03049","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streamspeech-simultaneous-speech-to-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03049"}},"official":{"repos":["ictnlp/streamspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-the-adaptive-relationship-between","slug":"rethinking-the-adaptive-relationship-between","title":"Rethinking the adaptive relationship between Encoder Layers and Decoder Layers","date":"2024-05-14","arxiv_id":"2405.08570","repositories_listed":1,"syntology":null},{"url":"/paper/centroid-based-efficient-minimum-bayes-risk","slug":"centroid-based-efficient-minimum-bayes-risk","title":"Centroid-Based Efficient Minimum Bayes Risk Decoding","date":"2024-02-17","arxiv_id":"2402.11197","repositories_listed":1,"syntology":null},{"url":"/paper/test-suites-task-evaluation-of-gender","slug":"test-suites-task-evaluation-of-gender","title":"Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INES","date":"2023-10-30","arxiv_id":"2310.19345","repositories_listed":1,"syntology":null},{"url":"/paper/multitude-large-scale-multilingual-machine","slug":"multitude-large-scale-multilingual-machine","title":"MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark","date":"2023-10-20","arxiv_id":"2310.13606","repositories_listed":1,"syntology":null},{"url":"/paper/on-synthetic-data-for-back-translation-2","slug":"on-synthetic-data-for-back-translation-2","title":"On Synthetic Data for Back Translation","date":"2023-10-20","arxiv_id":"2310.13675","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-the-importance-of-frequency-versus","slug":"assessing-the-importance-of-frequency-versus","title":"Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT","date":"2023-06-02","arxiv_id":"2306.01393","repositories_listed":1,"syntology":null},{"url":"/paper/back-translation-for-speech-to-text","slug":"back-translation-for-speech-to-text","title":"Back Translation for Speech-to-text Translation Without Transcripts","date":"2023-05-15","arxiv_id":"2305.08709","repositories_listed":1,"syntology":null},{"url":"/paper/escaping-the-sentence-level-paradigm-in","slug":"escaping-the-sentence-level-paradigm-in","title":"Escaping the sentence-level paradigm in machine translation","date":"2023-04-25","arxiv_id":"2304.12959","repositories_listed":1,"syntology":null},{"url":"/paper/speculative-decoding-with-big-little-decoder-1","slug":"speculative-decoding-with-big-little-decoder-1","title":"Speculative Decoding with Big Little Decoder","date":"2023-02-15","arxiv_id":"2302.07863","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speculative-decoding-with-big-little-decoder-1#ran","syntology_url":"https://syntology.ai/paper/2302.07863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07863"}},"official":{"repos":["kssteven418/biglittledecoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vega-mt-the-jd-explore-academy-translation","slug":"vega-mt-the-jd-explore-academy-translation","title":"Vega-MT: The JD Explore Academy Translation System for WMT22","date":"2022-09-20","arxiv_id":"2209.09444","repositories_listed":1,"syntology":null},{"url":"/paper/dims-distilling-multiple-steps-of-iterative","slug":"dims-distilling-multiple-steps-of-iterative","title":"DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation","date":"2022-06-07","arxiv_id":"2206.02999","repositories_listed":1,"syntology":null},{"url":"/paper/bi-simcut-a-simple-strategy-for-boosting-1","slug":"bi-simcut-a-simple-strategy-for-boosting-1","title":"Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation","date":"2022-06-06","arxiv_id":"2206.02368","repositories_listed":1,"syntology":null},{"url":"/paper/gaussian-multi-head-attention-for","slug":"gaussian-multi-head-attention-for","title":"Gaussian Multi-head Attention for Simultaneous Machine Translation","date":"2022-03-17","arxiv_id":"2203.09072","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/gaussian-multi-head-attention-for#ran","syntology_url":"https://syntology.ai/paper/2203.09072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09072"}},"official":{"repos":["ictnlp/gma"],"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/modeling-dual-read-write-paths-for","slug":"modeling-dual-read-write-paths-for","title":"Modeling Dual Read/Write Paths for Simultaneous Machine Translation","date":"2022-03-17","arxiv_id":"2203.09163","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/modeling-dual-read-write-paths-for#ran","syntology_url":"https://syntology.ai/paper/2203.09163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09163"}},"official":{"repos":["ictnlp/dual-paths"],"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":["found_in_text","official"]}}},{"url":"/paper/identifying-weaknesses-in-machine-translation","slug":"identifying-weaknesses-in-machine-translation","title":"Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET","date":"2022-02-10","arxiv_id":"2202.05148","repositories_listed":1,"syntology":null},{"url":"/paper/learning-and-analyzing-generation-order-for-1","slug":"learning-and-analyzing-generation-order-for-1","title":"Learning and Analyzing Generation Order for Undirected Sequence Models","date":"2021-12-16","arxiv_id":"2112.09097","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-rewrite-for-non-autoregressive","slug":"learning-to-rewrite-for-non-autoregressive","title":"Learning to Rewrite for Non-Autoregressive Neural Machine Translation","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-negation-in-neural-machine","slug":"revisiting-negation-in-neural-machine","title":"Revisiting Negation in Neural Machine Translation","date":"2021-07-26","arxiv_id":"2107.12203","repositories_listed":1,"syntology":null},{"url":"/paper/embedding-enhanced-giza-improving-alignment","slug":"embedding-enhanced-giza-improving-alignment","title":"Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry","date":"2021-04-18","arxiv_id":"2104.08721","repositories_listed":1,"syntology":null},{"url":"/paper/omninet-omnidirectional-representations-from","slug":"omninet-omnidirectional-representations-from","title":"OmniNet: Omnidirectional Representations from Transformers","date":"2021-03-01","arxiv_id":"2103.01075","repositories_listed":1,"syntology":null},{"url":"/paper/findings-of-the-wmt-2020-shared-task-on-chat","slug":"findings-of-the-wmt-2020-shared-task-on-chat","title":"Findings of the WMT 2020 Shared Task on Chat Translation","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vocabulary-adaptation-for-domain-adaptation","slug":"vocabulary-adaptation-for-domain-adaptation","title":"Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pronoun-targeted-fine-tuning-for-nmt-with","slug":"pronoun-targeted-fine-tuning-for-nmt-with","title":"Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses","date":"2020-10-15","arxiv_id":"2010.07638","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-refinement-in-the-continuous-space","slug":"iterative-refinement-in-the-continuous-space","title":"Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation","date":"2020-09-15","arxiv_id":"2009.07177","repositories_listed":1,"syntology":null},{"url":"/paper/engine-energy-based-inference-networks-for","slug":"engine-energy-based-inference-networks-for","title":"ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation","date":"2020-05-02","arxiv_id":"2005.00850","repositories_listed":1,"syntology":null},{"url":"/paper/hint-based-training-for-non-autoregressive-1","slug":"hint-based-training-for-non-autoregressive-1","title":"Hint-Based Training for Non-Autoregressive Machine Translation","date":"2019-09-15","arxiv_id":"1909.06708","repositories_listed":1,"syntology":null},{"url":null,"slug":"prompting-llms-length-control-for-isometric","title":"Prompting LLMs: Length Control for Isometric Machine Translation","date":"2025-06-05","arxiv_id":"2506.04855","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-text-compression-approach-using","title":"An Enhanced Text Compression Approach Using Transformer-based Language Models","date":"2024-12-15","arxiv_id":"2412.15250","repositories_listed":0,"syntology":null},{"url":"/paper/vetra-a-dataset-for-vehicle-tracking-in","slug":"vetra-a-dataset-for-vehicle-tracking-in","title":"VETRA: A Dataset for Vehicle Tracking in Aerial Imagery - New Challenges for Multi-Object Tracking","date":"2024-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-timestamp-information-for","title":"Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation","date":"2023-10-23","arxiv_id":"2310.14806","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-terminology-integration-into-machine","title":"Domain Terminology Integration into Machine Translation: Leveraging Large Language Models","date":"2023-10-22","arxiv_id":"2310.14451","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-large-language-model-for-end-to-end","title":"Tuning Large language model for End-to-end Speech Translation","date":"2023-10-03","arxiv_id":"2310.02050","repositories_listed":0,"syntology":null},{"url":null,"slug":"selfseg-a-self-supervised-sub-word","title":"SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation","date":"2023-07-31","arxiv_id":"2307.16400","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-connection-effective-connection-between","title":"Inter-connection: Effective Connection between Pre-trained Encoder and Decoder for Speech Translation","date":"2023-05-26","arxiv_id":"2305.16897","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-link-an-efficient-attention-based","title":"Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture","date":"2023-02-01","arxiv_id":"2302.00340","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-end-to-end-speech-translation-by-1","title":"Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data","date":"2022-12-04","arxiv_id":"2212.01778","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-robust-cross-modal-interactive-learning","title":"Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-enhanced-giza-improving-low-1","title":"Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"legonn-building-modular-encoder-decoder","title":"LegoNN: Building Modular Encoder-Decoder Models","date":"2022-06-07","arxiv_id":"2206.03318","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-automatic-and-manual-filtering","title":"Investigating automatic and manual filtering methods to produce MT-ready glossaries from existing ones","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hw-tscs-offline-speech-translation-system","title":"The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"docmt5-document-level-pre-training-of","title":"DOCmT5: Document-Level Pre-training of Multilingual Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-enhanced-giza-improving-low","title":"Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"non-autoregressive-neural-machine-translation-2","title":"Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-synthetic-data-for-back-translation","title":"On Synthetic Data for Back Translation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-training-on-symbiosis-networks-for-deep","title":"Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models","date":"2021-12-22","arxiv_id":"2112.11642","repositories_listed":0,"syntology":null},{"url":"/paper/docmt5-document-level-pretraining-of","slug":"docmt5-document-level-pretraining-of","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","date":"2021-12-16","arxiv_id":"2112.08709","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-end-to-end-speech-translation-by","title":"Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hw-tscs-participation-in-the-wmt-2021-news","title":"HW-TSC’s Participation in the WMT 2021 News Translation Shared Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"glossary-functionality-in-commercial-machine","title":"Glossary functionality in commercial machine translation: does it help? A first step to identify best practices for a language service provider","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-in-space-randomized-in-time","title":"Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training","date":"2021-06-22","arxiv_id":"2106.12089","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-attention-transformer-improving","title":"Predictive Attention Transformer: Improving Transformer with Attention Map Prediction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-university-of-edinburgh-uppsala","title":"The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sub-layer-functionalities-of","title":"On the Sub-Layer Functionalities of Transformer Decoder","date":"2020-10-06","arxiv_id":"2010.02648","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-talk-via-proactive-knowledge","title":"Learn to Talk via Proactive Knowledge Transfer","date":"2020-08-23","arxiv_id":"2008.10077","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-importance-of-local-information-in","title":"On the Importance of Local Information in Transformer Based Models","date":"2020-08-13","arxiv_id":"2008.05828","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-level-curriculum-learning-for-non","title":"Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation","date":"2020-07-17","arxiv_id":"2007.08772","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-posterior-collapse-with-mutual","title":"Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-autoregressive-nmt-with-non","title":"Improving Autoregressive NMT with Non-Autoregressive Model","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"character-level-transformer-based-neural","title":"Character-level Transformer-based Neural Machine Translation","date":"2020-05-22","arxiv_id":"2005.11239","repositories_listed":0,"syntology":null},{"url":null,"slug":"vocabulary-adaptation-for-distant-domain","title":"Vocabulary Adaptation for Distant Domain Adaptation in Neural Machine Translation","date":"2020-04-30","arxiv_id":"2004.14821","repositories_listed":0,"syntology":null},{"url":null,"slug":"ar-auto-repair-the-synthetic-data-for-neural","title":"AR: Auto-Repair the Synthetic Data for Neural Machine Translation","date":"2020-04-05","arxiv_id":"2004.02196","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalization-of-input-output-shared","title":"Normalization of Input-output Shared Embeddings in Text Generation Models","date":"2020-01-22","arxiv_id":"2001.07885","repositories_listed":0,"syntology":null},{"url":null,"slug":"monash-universitys-submissions-to-the-wngt","title":"Monash University's Submissions to the WNGT 2019 Document Translation Task","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-adaptive-scaling-for-learnable-residual","title":"Self-Adaptive Scaling for Learnable Residual Structure","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"proactive-sequence-generator-via-knowledge","title":"Proactive Sequence Generator via Knowledge Acquisition","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-adequacy-errors-in-neural-machine","title":"Exploring Adequacy Errors in Neural Machine Translation with the Help of Cross-Language Aligned Word Embeddings","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-wmt-2019-biomedical","title":"Findings of the WMT 2019 Biomedical Translation Shared Task: Evaluation for MEDLINE Abstracts and Biomedical Terminologies","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"johns-hopkins-university-submission-for-wmt","title":"Johns Hopkins University Submission for WMT News Translation Task","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rwth-aachen-university-machine","title":"The RWTH Aachen University Machine Translation Systems for WMT 2019","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hint-based-training-for-non-autoregressive","title":"Hint-based Training for Non-Autoregressive Translation","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-samsung-and-university-of-edinburghs","title":"The Samsung and University of Edinburgh’s submission to IWSLT17","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lig-cristal-system-for-the-wmt17-automatic","title":"LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task","date":"2017-07-17","arxiv_id":"1707.05118","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-university-of-edinburghs-systems","title":"The University of Edinburgh’s systems submission to the MT task at IWSLT","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-using-monolingual-corpora-in-neural","title":"On Using Monolingual Corpora in Neural Machine Translation","date":"2015-03-11","arxiv_id":"1503.03535","repositories_listed":0,"syntology":null}],"syntology_records":9,"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":8,"papers_where_code_ran_first_page":"/task/de-en/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":"ran","page":1,"of":1,"url":"/task/de-en/papers/ran/1","json":"/task/de-en/papers/ran/1.json","rows":8}],"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":"6ebf95839c482e63ab9ff6598fd119a82183774bf75c22dd04ac1e4b5a55068b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}