{"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/papers/26","list_of":"/task/sentence","task":"Sentence","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":26,"pages_in_order":108,"rows_per_page":100,"rows":[2501,2600],"of":10752,"counts":{"archive_papers_tagged":10752,"with_a_code_link":3811,"where_syntology_ran_a_sample":657,"not_listed_spam_title":0,"listed":10752,"listed_where_code_ran":657,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":544,"every_run_a_failure_of_syntologys_instrument":113,"listed_with_a_run_with_no_instrument_failure":544,"listed_every_run_a_failure_of_syntologys_instrument":113,"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"},"first_page":"/task/sentence","prev":"/task/sentence/papers/25","next":"/task/sentence/papers/27","papers":[{"url":"/paper/global-and-local-information-adjustment-for","slug":"global-and-local-information-adjustment-for","title":"Global and Local Information Adjustment for Semantic Similarity Evaluation","date":"2021-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/negation-in-norwegian-an-annotated-dataset","slug":"negation-in-norwegian-an-annotated-dataset","title":"Negation in Norwegian: an annotated dataset","date":"2021-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/paraphrastic-representations-at-scale","slug":"paraphrastic-representations-at-scale","title":"Paraphrastic Representations at Scale","date":"2021-04-30","arxiv_id":"2104.15114","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":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/paraphrastic-representations-at-scale#ran","syntology_url":"https://syntology.ai/paper/2104.15114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.15114"}},"official":{"repos":["jwieting/paraphrastic-representations-at-scale"],"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/amr-parsing-with-action-pointer-transformer","slug":"amr-parsing-with-action-pointer-transformer","title":"AMR Parsing with Action-Pointer Transformer","date":"2021-04-29","arxiv_id":"2104.14674","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amr-parsing-with-action-pointer-transformer#ran","syntology_url":"https://syntology.ai/paper/2104.14674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14674"}},"official":null}},{"url":"/paper/melbert-metaphor-detection-via-contextualized","slug":"melbert-metaphor-detection-via-contextualized","title":"MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories","date":"2021-04-28","arxiv_id":"2104.13615","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/melbert-metaphor-detection-via-contextualized#ran","syntology_url":"https://syntology.ai/paper/2104.13615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13615"}},"official":{"repos":["jin530/MelBERT"],"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/multi-view-inference-for-relation-extraction","slug":"multi-view-inference-for-relation-extraction","title":"Multi-view Inference for Relation Extraction with Uncertain Knowledge","date":"2021-04-28","arxiv_id":"2104.13579","repositories_listed":1,"syntology":null},{"url":"/paper/removing-word-level-spurious-alignment","slug":"removing-word-level-spurious-alignment","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","date":"2021-04-28","arxiv_id":"2104.13872","repositories_listed":1,"syntology":null},{"url":"/paper/morph-call-probing-morphosyntactic-content-of","slug":"morph-call-probing-morphosyntactic-content-of","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","date":"2021-04-26","arxiv_id":"2104.12847","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-break-prediction-with-bidirectional","slug":"phrase-break-prediction-with-bidirectional","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","date":"2021-04-26","arxiv_id":"2104.12395","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-post-editing-for-translating","slug":"automatic-post-editing-for-translating","title":"Automatic Post-Editing for Vietnamese","date":"2021-04-25","arxiv_id":"2104.12128","repositories_listed":1,"syntology":null},{"url":"/paper/open-intent-discovery-through-unsupervised","slug":"open-intent-discovery-through-unsupervised","title":"Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing","date":"2021-04-25","arxiv_id":"2104.12114","repositories_listed":1,"syntology":null},{"url":"/paper/qmul-sds-at-sciver-step-by-step-binary","slug":"qmul-sds-at-sciver-step-by-step-binary","title":"QMUL-SDS at SCIVER: Step-by-Step Binary Classification for Scientific Claim Verification","date":"2021-04-23","arxiv_id":"2104.11572","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-document-representations-for-large","slug":"revisiting-document-representations-for-large","title":"Revisiting Document Representations for Large-Scale Zero-Shot Learning","date":"2021-04-21","arxiv_id":"2104.10355","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/revisiting-document-representations-for-large#ran","syntology_url":"https://syntology.ai/paper/2104.10355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10355"}},"official":{"repos":["heendung/vs-zsl"],"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/understanding-synonymous-referring","slug":"understanding-synonymous-referring","title":"Understanding Synonymous Referring Expressions via Contrastive Features","date":"2021-04-20","arxiv_id":"2104.10156","repositories_listed":1,"syntology":null},{"url":"/paper/improving-cross-modal-alignment-in-vision","slug":"improving-cross-modal-alignment-in-vision","title":"Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information","date":"2021-04-19","arxiv_id":"2104.09580","repositories_listed":1,"syntology":null},{"url":"/paper/refining-targeted-syntactic-evaluation-of","slug":"refining-targeted-syntactic-evaluation-of","title":"Refining Targeted Syntactic Evaluation of Language Models","date":"2021-04-19","arxiv_id":"2104.09635","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/refining-targeted-syntactic-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2104.09635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09635"}},"official":{"repos":["bnewm0609/refining-tse"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/flexible-operations-for-natural-language","slug":"flexible-operations-for-natural-language","title":"Flexible Generation of Natural Language Deductions","date":"2021-04-18","arxiv_id":"2104.08825","repositories_listed":1,"syntology":null},{"url":"/paper/stream-level-latency-evaluation-for","slug":"stream-level-latency-evaluation-for","title":"Stream-level Latency Evaluation for Simultaneous Machine Translation","date":"2021-04-18","arxiv_id":"2104.08817","repositories_listed":1,"syntology":null},{"url":"/paper/attacking-text-classifiers-via-sentence","slug":"attacking-text-classifiers-via-sentence","title":"R&R: Metric-guided Adversarial Sentence Generation","date":"2021-04-17","arxiv_id":"2104.08453","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attacking-text-classifiers-via-sentence#ran","syntology_url":"https://syntology.ai/paper/2104.08453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08453"}},"official":{"repos":["DAI-Lab/fibber"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-transformer-networks-for","slug":"hierarchical-transformer-networks-for","title":"Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-04-17","arxiv_id":"2104.08444","repositories_listed":1,"syntology":null},{"url":"/paper/improving-zero-shot-cross-lingual-transfer","slug":"improving-zero-shot-cross-lingual-transfer","title":"Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training","date":"2021-04-17","arxiv_id":"2104.08645","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-alignment-with-parallel-documents","slug":"sentence-alignment-with-parallel-documents","title":"Sentence Alignment with Parallel Documents Facilitates Biomedical Machine Translation","date":"2021-04-17","arxiv_id":"2104.08588","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/sentence-alignment-with-parallel-documents#ran","syntology_url":"https://syntology.ai/paper/2104.08588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08588"}},"official":{"repos":["luosx18/biomedical-sentence-aligner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-effective-and-self-supervised","slug":"fast-effective-and-self-supervised","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","date":"2021-04-16","arxiv_id":"2104.08027","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/fast-effective-and-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2104.08027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08027"}},"official":{"repos":["cambridgeltl/mirror-bert"],"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/re-tacred-addressing-shortcomings-of-the","slug":"re-tacred-addressing-shortcomings-of-the","title":"Re-TACRED: Addressing Shortcomings of the TACRED Dataset","date":"2021-04-16","arxiv_id":"2104.08398","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/re-tacred-addressing-shortcomings-of-the#ran","syntology_url":"https://syntology.ai/paper/2104.08398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08398"}},"official":{"repos":["gstoica27/Re-TACRED"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/bilingual-alignment-transfers-to-multilingual","slug":"bilingual-alignment-transfers-to-multilingual","title":"Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining","date":"2021-04-15","arxiv_id":"2104.07642","repositories_listed":1,"syntology":null},{"url":"/paper/detect-and-classify-joint-span-detection-and","slug":"detect-and-classify-joint-span-detection-and","title":"Detect and Classify -- Joint Span Detection and Classification for Health Outcomes","date":"2021-04-15","arxiv_id":"2104.07789","repositories_listed":1,"syntology":null},{"url":"/paper/first-the-worst-finding-better-gender","slug":"first-the-worst-finding-better-gender","title":"First the worst: Finding better gender translations during beam search","date":"2021-04-15","arxiv_id":"2104.07429","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-permuted-paragraph-generation","slug":"sentence-permuted-paragraph-generation","title":"Sentence-Permuted Paragraph Generation","date":"2021-04-15","arxiv_id":"2104.07228","repositories_listed":1,"syntology":null},{"url":"/paper/iga-an-intent-guided-authoring-assistant","slug":"iga-an-intent-guided-authoring-assistant","title":"IGA : An Intent-Guided Authoring Assistant","date":"2021-04-14","arxiv_id":"2104.07000","repositories_listed":1,"syntology":null},{"url":"/paper/reformulating-sentence-ordering-as","slug":"reformulating-sentence-ordering-as","title":"Is Everything in Order? A Simple Way to Order Sentences","date":"2021-04-14","arxiv_id":"2104.07064","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/reformulating-sentence-ordering-as#ran","syntology_url":"https://syntology.ai/paper/2104.07064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07064"}},"official":{"repos":["fabrahman/rebart"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discourse-probing-of-pretrained-language","slug":"discourse-probing-of-pretrained-language","title":"Discourse Probing of Pretrained Language Models","date":"2021-04-13","arxiv_id":"2104.05882","repositories_listed":1,"syntology":null},{"url":"/paper/document-level-event-argument-extraction-by","slug":"document-level-event-argument-extraction-by","title":"Document-Level Event Argument Extraction by Conditional Generation","date":"2021-04-13","arxiv_id":"2104.05919","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/document-level-event-argument-extraction-by#ran","syntology_url":"https://syntology.ai/paper/2104.05919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05919"}},"official":{"repos":["raspberryice/gen-arg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fall-of-giants-how-popular-text-based-mlaas","slug":"fall-of-giants-how-popular-text-based-mlaas","title":"Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack","date":"2021-04-13","arxiv_id":"2104.05996","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-discontinuous-to-continuous-parsing","slug":"reducing-discontinuous-to-continuous-parsing","title":"Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering","date":"2021-04-13","arxiv_id":"2104.06239","repositories_listed":1,"syntology":null},{"url":"/paper/continual-learning-for-text-classification","slug":"continual-learning-for-text-classification","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","date":"2021-04-12","arxiv_id":"2104.05489","repositories_listed":1,"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/continual-learning-for-text-classification#ran","syntology_url":"https://syntology.ai/paper/2104.05489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05489"}},"official":{"repos":["GT-SALT/IDBR"],"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/evaluating-saliency-methods-for-neural","slug":"evaluating-saliency-methods-for-neural","title":"Evaluating Saliency Methods for Neural Language Models","date":"2021-04-12","arxiv_id":"2104.05824","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-language-models-predict-human","slug":"multilingual-language-models-predict-human","title":"Multilingual Language Models Predict Human Reading Behavior","date":"2021-04-12","arxiv_id":"2104.05433","repositories_listed":1,"syntology":null},{"url":"/paper/samanantar-the-largest-publicly-available","slug":"samanantar-the-largest-publicly-available","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","date":"2021-04-12","arxiv_id":"2104.05596","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-semantics-and-syntax-in","slug":"disentangling-semantics-and-syntax-in","title":"Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models","date":"2021-04-11","arxiv_id":"2104.05115","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-explainable-parse","slug":"unsupervised-learning-of-explainable-parse","title":"Unsupervised Learning of Explainable Parse Trees for Improved Generalisation","date":"2021-04-11","arxiv_id":"2104.04998","repositories_listed":1,"syntology":null},{"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/nli-data-sanity-check-assessing-the-effect-of","slug":"nli-data-sanity-check-assessing-the-effect-of","title":"NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance","date":"2021-04-10","arxiv_id":"2104.04751","repositories_listed":1,"syntology":null},{"url":"/paper/sentiment-based-candidate-selection-for-nmt","slug":"sentiment-based-candidate-selection-for-nmt","title":"Sentiment-based Candidate Selection for NMT","date":"2021-04-10","arxiv_id":"2104.04840","repositories_listed":1,"syntology":null},{"url":"/paper/utnlp-at-semeval-2021-task-5-a-comparative","slug":"utnlp-at-semeval-2021-task-5-a-comparative","title":"UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models","date":"2021-04-10","arxiv_id":"2104.04770","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-neural-network-predictions-on","slug":"explaining-neural-network-predictions-on","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","date":"2021-04-09","arxiv_id":"2104.04488","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/explaining-neural-network-predictions-on#ran","syntology_url":"https://syntology.ai/paper/2104.04488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04488"}},"official":{"repos":["UVa-NLP/GMASK"],"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":["official"]}}},{"url":"/paper/whiteningbert-an-easy-unsupervised-sentence","slug":"whiteningbert-an-easy-unsupervised-sentence","title":"WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach","date":"2021-04-05","arxiv_id":"2104.01767","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-role-of-bert-token","slug":"exploring-the-role-of-bert-token","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","date":"2021-04-03","arxiv_id":"2104.01477","repositories_listed":1,"syntology":null},{"url":"/paper/acquiring-a-formality-informed-lexical","slug":"acquiring-a-formality-informed-lexical","title":"Acquiring a Formality-Informed Lexical Resource for Style Analysis","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adaptation-of-back-translation-to-automatic","slug":"adaptation-of-back-translation-to-automatic","title":"Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/are-neural-networks-extracting-linguistic","slug":"are-neural-networks-extracting-linguistic","title":"Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-relational-graph","slug":"attention-based-relational-graph","title":"Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-neural-machine-translation-with-1","slug":"context-aware-neural-machine-translation-with-1","title":"Context-aware Neural Machine Translation with Mini-batch Embedding","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/discourse-aware-unsupervised-summarization","slug":"discourse-aware-unsupervised-summarization","title":"Discourse-Aware Unsupervised Summarization for Long Scientific Documents","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/document-level-grammatical-error-correction","slug":"document-level-grammatical-error-correction","title":"Document-level grammatical error correction","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enpar-enhancing-entity-and-entity-pair","slug":"enpar-enhancing-entity-and-entity-pair","title":"ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/expanding-retrieving-and-infilling","slug":"expanding-retrieving-and-infilling","title":"Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-definitions-for-frame","slug":"exploiting-definitions-for-frame","title":"Exploiting Definitions for Frame Identification","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-and-code-switching-asr","slug":"multilingual-and-code-switching-asr","title":"Multilingual and code-switching ASR challenges for low resource Indian languages","date":"2021-04-01","arxiv_id":"2104.00235","repositories_listed":1,"syntology":null},{"url":"/paper/multireqa-a-cross-domain-evaluation","slug":"multireqa-a-cross-domain-evaluation","title":"MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nlquad-a-non-factoid-long-question-answering","slug":"nlquad-a-non-factoid-long-question-answering","title":"NLQuAD: A Non-Factoid Long Question Answering Data Set","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/parsing-argumentative-structure-in-english-as","slug":"parsing-argumentative-structure-in-english-as","title":"Parsing Argumentative Structure in English-as-Foreign-Language Essays","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/punktuator-a-multilingual-punctuation","slug":"punktuator-a-multilingual-punctuation","title":"PunKtuator: A Multilingual Punctuation Restoration System for Spoken and Written Text","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text-to-image-generation-with-semantic","slug":"text-to-image-generation-with-semantic","title":"Text to Image Generation with Semantic-Spatial Aware GAN","date":"2021-04-01","arxiv_id":"2104.00567","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-approach-to-multilingual-user","slug":"unsupervised-approach-to-multilingual-user","title":"Unsupervised Approach to Multilingual User Comments Summarization","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/divide-and-rule-training-context-aware-multi","slug":"divide-and-rule-training-context-aware-multi","title":"Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models","date":"2021-03-31","arxiv_id":"2103.17151","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-neural-machine-translation-for","slug":"leveraging-neural-machine-translation-for","title":"Leveraging Neural Machine Translation for Word Alignment","date":"2021-03-31","arxiv_id":"2103.17250","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-euphemism-detection-and","slug":"self-supervised-euphemism-detection-and","title":"Self-Supervised Euphemism Detection and Identification for Content Moderation","date":"2021-03-31","arxiv_id":"2103.16808","repositories_listed":1,"syntology":null},{"url":"/paper/be-careful-about-poisoned-word-embeddings","slug":"be-careful-about-poisoned-word-embeddings","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","date":"2021-03-29","arxiv_id":"2103.15543","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-visualization-via-dictionary","slug":"transformer-visualization-via-dictionary","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","date":"2021-03-29","arxiv_id":"2103.15949","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/transformer-visualization-via-dictionary#ran","syntology_url":"https://syntology.ai/paper/2103.15949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15949"}},"official":{"repos":["zeyuyun1/transformervis"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-vision-and-language-from-the-video","slug":"bridging-vision-and-language-from-the-video","title":"A Comprehensive Review of the Video-to-Text Problem","date":"2021-03-27","arxiv_id":"2103.14785","repositories_listed":1,"syntology":null},{"url":"/paper/synthesis-of-compositional-animations-from","slug":"synthesis-of-compositional-animations-from","title":"Synthesis of Compositional Animations from Textual Descriptions","date":"2021-03-26","arxiv_id":"2103.14675","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/synthesis-of-compositional-animations-from#ran","syntology_url":"https://syntology.ai/paper/2103.14675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14675"}},"official":{"repos":["anindita127/complextext2animation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/turning-transformer-attention-weights-into","slug":"turning-transformer-attention-weights-into","title":"Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers","date":"2021-03-26","arxiv_id":"2103.14465","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-document-embedding-via","slug":"unsupervised-document-embedding-via","title":"Unsupervised Document Embedding via Contrastive Augmentation","date":"2021-03-26","arxiv_id":"2103.14542","repositories_listed":1,"syntology":null},{"url":"/paper/exercise-i-thought-you-said-extra-fries","slug":"exercise-i-thought-you-said-extra-fries","title":"Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysis","date":"2021-03-23","arxiv_id":"2103.12377","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":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/exercise-i-thought-you-said-extra-fries#ran","syntology_url":"https://syntology.ai/paper/2103.12377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12377"}},"official":{"repos":["LCS2-IIITD/MHA-MEME"],"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/human-like-controllable-image-captioning-with","slug":"human-like-controllable-image-captioning-with","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","date":"2021-03-22","arxiv_id":"2103.12204","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/human-like-controllable-image-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2103.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12204"}},"official":{"repos":["mad-red/VSR-guided-CIC"],"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/congolese-swahili-machine-translation-for","slug":"congolese-swahili-machine-translation-for","title":"Congolese Swahili Machine Translation for Humanitarian Response","date":"2021-03-19","arxiv_id":"2103.10734","repositories_listed":1,"syntology":null},{"url":"/paper/generating-ccg-categories","slug":"generating-ccg-categories","title":"Generating CCG Categories","date":"2021-03-15","arxiv_id":"2103.08139","repositories_listed":1,"syntology":null},{"url":"/paper/mermaid-metaphor-generation-with-symbolism","slug":"mermaid-metaphor-generation-with-symbolism","title":"MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding","date":"2021-03-11","arxiv_id":"2103.06779","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/mermaid-metaphor-generation-with-symbolism#ran","syntology_url":"https://syntology.ai/paper/2103.06779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06779"}},"official":{"repos":["tuhinjubcse/MetaphorGenNAACL2021"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/iterative-shrinking-for-referring-expression","slug":"iterative-shrinking-for-referring-expression","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","date":"2021-03-09","arxiv_id":"2103.05187","repositories_listed":1,"syntology":null},{"url":"/paper/local-word-statistics-affect-reading-times","slug":"local-word-statistics-affect-reading-times","title":"Local word statistics affect reading times independently of surprisal","date":"2021-03-07","arxiv_id":"2103.04469","repositories_listed":1,"syntology":null},{"url":"/paper/readnet-a-hierarchical-transformer-framework","slug":"readnet-a-hierarchical-transformer-framework","title":"ReadNet: A Hierarchical Transformer Framework for Web Article Readability Analysis","date":"2021-03-06","arxiv_id":"2103.04083","repositories_listed":1,"syntology":null},{"url":"/paper/error-driven-fixed-budget-asr-personalization","slug":"error-driven-fixed-budget-asr-personalization","title":"Error-driven Fixed-Budget ASR Personalization for Accented Speakers","date":"2021-03-04","arxiv_id":"2103.03142","repositories_listed":1,"syntology":null},{"url":"/paper/an-iterative-contextualization-algorithm-with","slug":"an-iterative-contextualization-algorithm-with","title":"An Iterative Contextualization Algorithm with Second-Order Attention","date":"2021-03-03","arxiv_id":"2103.02190","repositories_listed":1,"syntology":null},{"url":"/paper/multisubs-a-large-scale-multimodal-and","slug":"multisubs-a-large-scale-multimodal-and","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","date":"2021-03-02","arxiv_id":"2103.01910","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-deep-convolution-neural-network","slug":"pre-trained-deep-convolution-neural-network","title":"Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition","date":"2021-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-word-segmentation-with-bi","slug":"unsupervised-word-segmentation-with-bi","title":"Unsupervised Word Segmentation with Bi-directional Neural Language Model","date":"2021-03-02","arxiv_id":"2103.01421","repositories_listed":1,"syntology":null},{"url":"/paper/cryptonite-a-cryptic-crossword-benchmark-for","slug":"cryptonite-a-cryptic-crossword-benchmark-for","title":"Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language","date":"2021-03-01","arxiv_id":"2103.01242","repositories_listed":1,"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/cryptonite-a-cryptic-crossword-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2103.01242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01242"}},"official":{"repos":["aviaefrat/cryptonite"],"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/creating-a-universal-dependencies-treebank-of","slug":"creating-a-universal-dependencies-treebank-of","title":"Creating a Universal Dependencies Treebank of Spoken Frisian-Dutch Code-switched Data","date":"2021-02-22","arxiv_id":"2102.11152","repositories_listed":1,"syntology":null},{"url":"/paper/multi-domain-adaptation-in-neural-machine","slug":"multi-domain-adaptation-in-neural-machine","title":"Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging","date":"2021-02-19","arxiv_id":"2102.10160","repositories_listed":1,"syntology":null},{"url":"/paper/non-autoregressive-text-generation-with-pre","slug":"non-autoregressive-text-generation-with-pre","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","date":"2021-02-16","arxiv_id":"2102.08220","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-language-encoding-in-learning","slug":"revisiting-language-encoding-in-learning","title":"Revisiting Language Encoding in Learning Multilingual Representations","date":"2021-02-16","arxiv_id":"2102.08357","repositories_listed":1,"syntology":null},{"url":"/paper/annotation-cleaning-for-the-msr-video-to-text","slug":"annotation-cleaning-for-the-msr-video-to-text","title":"The MSR-Video to Text Dataset with Clean Annotations","date":"2021-02-12","arxiv_id":"2102.06448","repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-model-for-entity-level-relation","slug":"an-end-to-end-model-for-entity-level-relation","title":"An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning","date":"2021-02-11","arxiv_id":"2102.05980","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/unsupervised-extractive-summarization-using","slug":"unsupervised-extractive-summarization-using","title":"Unsupervised Extractive Summarization using Pointwise Mutual Information","date":"2021-02-11","arxiv_id":"2102.06272","repositories_listed":1,"syntology":null},{"url":"/paper/how-true-is-gpt-2-an-empirical-analysis-of","slug":"how-true-is-gpt-2-an-empirical-analysis-of","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","date":"2021-02-08","arxiv_id":"2102.04130","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-true-is-gpt-2-an-empirical-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2102.04130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04130"}},"official":{"repos":["oxai/intersectional_gpt2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spoiler-alert-using-natural-language","slug":"spoiler-alert-using-natural-language","title":"Spoiler Alert: Using Natural Language Processing to Detect Spoilers in Book Reviews","date":"2021-02-07","arxiv_id":"2102.03882","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-sentence-embeddings-by-manifold","slug":"unsupervised-sentence-embeddings-by-manifold","title":"Unsupervised Sentence-embeddings by Manifold Approximation and Projection","date":"2021-02-07","arxiv_id":"2102.03795","repositories_listed":1,"syntology":null},{"url":"/paper/an-improved-baseline-for-sentence-level","slug":"an-improved-baseline-for-sentence-level","title":"An Improved Baseline for Sentence-level Relation Extraction","date":"2021-02-02","arxiv_id":"2102.01373","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-email-zoning","slug":"multilingual-email-zoning","title":"Multilingual Email Zoning","date":"2021-01-31","arxiv_id":"2102.00461","repositories_listed":1,"syntology":null}],"record_sha256":"92f3a9aed09c4ccdd9f156af217bf95da11d300189bae5d4e270fe981f931b0b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}