{"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/question-answering/papers/6","list_of":"/task/question-answering","task":"Question Answering","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":6,"pages_in_order":109,"rows_per_page":100,"rows":[501,600],"of":10817,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"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/question-answering","prev":"/task/question-answering/papers/5","next":"/task/question-answering/papers/7","papers":[{"url":"/paper/qdrop-randomly-dropping-quantization-for-1","slug":"qdrop-randomly-dropping-quantization-for-1","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","date":"2022-03-11","arxiv_id":"2203.05740","repositories_listed":2,"syntology":{"n":19,"n_ran":14,"n_constructed":5,"n_ran_checked":6,"n_instrument":8,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"14 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/qdrop-randomly-dropping-quantization-for-1#ran","syntology_url":"https://syntology.ai/paper/2203.05740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05740"}},"official":{"repos":["modeltc/mqbench","wimh966/QDrop"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dataset-for-medical-instructional-video","slug":"a-dataset-for-medical-instructional-video","title":"A Dataset for Medical Instructional Video Classification and Question Answering","date":"2022-01-30","arxiv_id":"2201.12888","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-for-medical-instructional-video#ran","syntology_url":"https://syntology.ai/paper/2201.12888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12888"}},"official":{"repos":["deepaknlp/medvidqacl"],"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/rumedbench-a-russian-medical-language","slug":"rumedbench-a-russian-medical-language","title":"RuMedBench: A Russian Medical Language Understanding Benchmark","date":"2022-01-17","arxiv_id":"2201.06499","repositories_listed":2,"syntology":null},{"url":"/paper/scrolls-standardized-comparison-over-long","slug":"scrolls-standardized-comparison-over-long","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","date":"2022-01-10","arxiv_id":"2201.03533","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scrolls-standardized-comparison-over-long#ran","syntology_url":"https://syntology.ai/paper/2201.03533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03533"}},"official":{"repos":["tau-nlp/scrolls"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mumuqa-multimedia-multi-hop-news-question","slug":"mumuqa-multimedia-multi-hop-news-question","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","date":"2021-12-20","arxiv_id":"2112.10728","repositories_listed":2,"syntology":null},{"url":"/paper/webgpt-browser-assisted-question-answering","slug":"webgpt-browser-assisted-question-answering","title":"WebGPT: Browser-assisted question-answering with human feedback","date":"2021-12-17","arxiv_id":"2112.09332","repositories_listed":2,"syntology":null},{"url":"/paper/ditch-the-gold-standard-re-evaluating-1","slug":"ditch-the-gold-standard-re-evaluating-1","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","date":"2021-12-16","arxiv_id":"2112.08812","repositories_listed":2,"syntology":null},{"url":"/paper/utilizing-evidence-spans-via-sequence-level","slug":"utilizing-evidence-spans-via-sequence-level","title":"Long Context Question Answering via Supervised Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.08777","repositories_listed":2,"syntology":null},{"url":"/paper/kge-cl-contrastive-learning-of-knowledge","slug":"kge-cl-contrastive-learning-of-knowledge","title":"KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings","date":"2021-12-09","arxiv_id":"2112.04871","repositories_listed":2,"syntology":null},{"url":"/paper/improving-language-models-by-retrieving-from","slug":"improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","arxiv_id":"2112.04426","repositories_listed":2,"syntology":{"n":23,"n_ran":16,"n_constructed":5,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":3,"n_no_contract":11,"n_pointer_only":3,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/improving-language-models-by-retrieving-from#ran","syntology_url":"https://syntology.ai/paper/2112.04426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04426"}},"official":null}},{"url":"/paper/assistsr-affordance-centric-question-driven","slug":"assistsr-affordance-centric-question-driven","title":"AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant","date":"2021-11-30","arxiv_id":"2111.15050","repositories_listed":2,"syntology":null},{"url":"/paper/searching-the-search-space-of-vision-1","slug":"searching-the-search-space-of-vision-1","title":"Searching the Search Space of Vision Transformer","date":"2021-11-29","arxiv_id":"2111.14725","repositories_listed":2,"syntology":null},{"url":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","repositories_listed":2,"syntology":null},{"url":"/paper/vivqa-vietnamese-visual-question-answering","slug":"vivqa-vietnamese-visual-question-answering","title":"ViVQA: Vietnamese Visual Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/metaicl-learning-to-learn-in-context","slug":"metaicl-learning-to-learn-in-context","title":"MetaICL: Learning to Learn In Context","date":"2021-10-29","arxiv_id":"2110.15943","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/metaicl-learning-to-learn-in-context#ran","syntology_url":"https://syntology.ai/paper/2110.15943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15943"}},"official":{"repos":["facebookresearch/metaicl"],"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/deepage-answering-questions-in-portuguese","slug":"deepage-answering-questions-in-portuguese","title":"DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment","date":"2021-10-19","arxiv_id":"2110.10015","repositories_listed":2,"syntology":null},{"url":"/paper/label-descriptive-patterns-and-their","slug":"label-descriptive-patterns-and-their","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","date":"2021-10-18","arxiv_id":"2110.09599","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/label-descriptive-patterns-and-their#ran","syntology_url":"https://syntology.ai/paper/2110.09599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09599"}},"official":{"repos":["uds-lsv/premise"],"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/bbq-a-hand-built-bias-benchmark-for-question","slug":"bbq-a-hand-built-bias-benchmark-for-question","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","date":"2021-10-15","arxiv_id":"2110.08193","repositories_listed":2,"syntology":null},{"url":"/paper/can-explanations-be-useful-for-calibrating","slug":"can-explanations-be-useful-for-calibrating","title":"Can Explanations Be Useful for Calibrating Black Box Models?","date":"2021-10-14","arxiv_id":"2110.07586","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/can-explanations-be-useful-for-calibrating#ran","syntology_url":"https://syntology.ai/paper/2110.07586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07586"}},"official":{"repos":["xiye17/interpcalib"],"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/conditionalqa-a-complex-reading-comprehension","slug":"conditionalqa-a-complex-reading-comprehension","title":"ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers","date":"2021-10-13","arxiv_id":"2110.06884","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/conditionalqa-a-complex-reading-comprehension#ran","syntology_url":"https://syntology.ai/paper/2110.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06884"}},"official":{"repos":["haitian-sun/conditionalqa"],"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/salient-phrase-aware-dense-retrieval-can-a","slug":"salient-phrase-aware-dense-retrieval-can-a","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","date":"2021-10-13","arxiv_id":"2110.06918","repositories_listed":2,"syntology":null},{"url":"/paper/systematic-inequalities-in-language","slug":"systematic-inequalities-in-language","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","date":"2021-10-13","arxiv_id":"2110.06733","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/systematic-inequalities-in-language#ran","syntology_url":"https://syntology.ai/paper/2110.06733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06733"}},"official":{"repos":["neubig/globalutility"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/what-makes-sentences-semantically-related-a","slug":"what-makes-sentences-semantically-related-a","title":"What Makes Sentences Semantically Related: A Textual Relatedness Dataset and Empirical Study","date":"2021-10-10","arxiv_id":"2110.04845","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-makes-sentences-semantically-related-a#ran","syntology_url":"https://syntology.ai/paper/2110.04845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04845"}},"official":{"repos":["priya22/semantic-textual-relatedness"],"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/towards-continual-knowledge-learning-of","slug":"towards-continual-knowledge-learning-of","title":"Towards Continual Knowledge Learning of Language Models","date":"2021-10-07","arxiv_id":"2110.03215","repositories_listed":2,"syntology":null},{"url":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}},"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/entqa-entity-linking-as-question-answering","slug":"entqa-entity-linking-as-question-answering","title":"EntQA: Entity Linking as Question Answering","date":"2021-10-05","arxiv_id":"2110.02369","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":3,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entqa-entity-linking-as-question-answering#ran","syntology_url":"https://syntology.ai/paper/2110.02369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02369"}},"official":{"repos":["wenzhengzhang/entqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/weakly-supervised-visual-retriever-reader-for","slug":"weakly-supervised-visual-retriever-reader-for","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","date":"2021-09-09","arxiv_id":"2109.04014","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weakly-supervised-visual-retriever-reader-for#ran","syntology_url":"https://syntology.ai/paper/2109.04014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04014"}},"official":{"repos":["luomancs/retriever_reader_for_okvqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/it-is-ai-s-turn-to-ask-human-a-question","slug":"it-is-ai-s-turn-to-ask-human-a-question","title":"It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books","date":"2021-09-08","arxiv_id":"2109.03423","repositories_listed":2,"syntology":null},{"url":"/paper/general-purpose-question-answering-with-macaw","slug":"general-purpose-question-answering-with-macaw","title":"General-Purpose Question-Answering with Macaw","date":"2021-09-06","arxiv_id":"2109.02593","repositories_listed":2,"syntology":null},{"url":"/paper/transformer-models-for-text-coherence","slug":"transformer-models-for-text-coherence","title":"Transformer Models for Text Coherence Assessment","date":"2021-09-05","arxiv_id":"2109.02176","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-multilingual-capabilities-of-very","slug":"on-the-multilingual-capabilities-of-very","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-08-30","arxiv_id":"2108.13349","repositories_listed":2,"syntology":null},{"url":"/paper/dealing-with-typos-for-bert-based-passage","slug":"dealing-with-typos-for-bert-based-passage","title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking","date":"2021-08-27","arxiv_id":"2108.12139","repositories_listed":2,"syntology":null},{"url":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","repositories_listed":2,"syntology":{"n":37,"n_ran":22,"n_constructed":8,"n_ran_checked":16,"n_instrument":6,"n_unverified":15,"n_honours":1,"n_violates":3,"n_no_contract":12,"n_pointer_only":32,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"official":null}},{"url":"/paper/smedbert-a-knowledge-enhanced-pre-trained","slug":"smedbert-a-knowledge-enhanced-pre-trained","title":"SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining","date":"2021-08-20","arxiv_id":"2108.08983","repositories_listed":2,"syntology":null},{"url":"/paper/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/fedmatch-federated-learning-over","slug":"fedmatch-federated-learning-over","title":"FedMatch: Federated Learning Over Heterogeneous Question Answering Data","date":"2021-08-11","arxiv_id":"2108.05069","repositories_listed":2,"syntology":null},{"url":"/paper/separating-skills-and-concepts-for-novel-1","slug":"separating-skills-and-concepts-for-novel-1","title":"Separating Skills and Concepts for Novel Visual Question Answering","date":"2021-07-19","arxiv_id":"2107.09106","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/separating-skills-and-concepts-for-novel-1#ran","syntology_url":"https://syntology.ai/paper/2107.09106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09106"}},"official":{"repos":["SpencerWhitehead/novelvqa"],"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":["listed","official"]}}},{"url":"/paper/spanish-language-models","slug":"spanish-language-models","title":"MarIA: Spanish Language Models","date":"2021-07-15","arxiv_id":"2107.07253","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-visual-question-answering-using","slug":"zero-shot-visual-question-answering-using","title":"Zero-shot Visual Question Answering using Knowledge Graph","date":"2021-07-12","arxiv_id":"2107.05348","repositories_listed":2,"syntology":null},{"url":"/paper/abcd-a-graph-framework-to-convert-complex","slug":"abcd-a-graph-framework-to-convert-complex","title":"ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences","date":"2021-06-22","arxiv_id":"2106.12027","repositories_listed":2,"syntology":null},{"url":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","repositories_listed":2,"syntology":null},{"url":"/paper/kaggledbqa-realistic-evaluation-of-text-to","slug":"kaggledbqa-realistic-evaluation-of-text-to","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","date":"2021-06-22","arxiv_id":"2106.11455","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-multi-document-reader","slug":"end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","arxiv_id":"2106.05346","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}},"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/disfl-qa-a-benchmark-dataset-for","slug":"disfl-qa-a-benchmark-dataset-for","title":"Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering","date":"2021-06-08","arxiv_id":"2106.04016","repositories_listed":2,"syntology":null},{"url":"/paper/question-answering-over-temporal-knowledge","slug":"question-answering-over-temporal-knowledge","title":"Question Answering Over Temporal Knowledge Graphs","date":"2021-06-03","arxiv_id":"2106.01515","repositories_listed":2,"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":1,"phrase":"0 ran · 2 unverified","sample_list":"/paper/question-answering-over-temporal-knowledge#ran","syntology_url":"https://syntology.ai/paper/2106.01515","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01515"}},"official":{"repos":["apoorvumang/CronKGQA"],"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/spartqa-a-textual-question-answering-1","slug":"spartqa-a-textual-question-answering-1","title":"SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning","date":"2021-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multiple-meta-model-quantifying-for-medical","slug":"multiple-meta-model-quantifying-for-medical","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","date":"2021-05-19","arxiv_id":"2105.08913","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 3 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-meta-model-quantifying-for-medical#ran","syntology_url":"https://syntology.ai/paper/2105.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08913"}},"official":{"repos":["aioz-ai/MICCAI21_MMQ"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/next-qa-next-phase-of-question-answering-to","slug":"next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","date":"2021-05-18","arxiv_id":"2105.08276","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/next-qa-next-phase-of-question-answering-to#ran","syntology_url":"https://syntology.ai/paper/2105.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08276"}},"official":{"repos":["doc-doc/NExT-QA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-generative-symbolic-model-for-more-general","slug":"a-generative-symbolic-model-for-more-general","title":"Towards General Natural Language Understanding with Probabilistic Worldbuilding","date":"2021-05-06","arxiv_id":"2105.02486","repositories_listed":2,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/a-generative-symbolic-model-for-more-general#ran","syntology_url":"https://syntology.ai/paper/2105.02486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02486"}},"official":{"repos":["asaparov/fictionalgeoqa","asaparov/pwl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","repositories_listed":2,"syntology":null},{"url":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","repositories_listed":2,"syntology":null},{"url":"/paper/when-does-pretraining-help-assessing-self","slug":"when-does-pretraining-help-assessing-self","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","date":"2021-04-18","arxiv_id":"2104.08671","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/when-does-pretraining-help-assessing-self#ran","syntology_url":"https://syntology.ai/paper/2104.08671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08671"}},"official":{"repos":["reglab/casehold"],"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":["listed","official"]}}},{"url":"/paper/indonlg-benchmark-and-resources-for","slug":"indonlg-benchmark-and-resources-for","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","date":"2021-04-16","arxiv_id":"2104.08200","repositories_listed":2,"syntology":null},{"url":"/paper/towards-general-purpose-vision-systems","slug":"towards-general-purpose-vision-systems","title":"Towards General Purpose Vision Systems","date":"2021-04-01","arxiv_id":"2104.00743","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/towards-general-purpose-vision-systems#ran","syntology_url":"https://syntology.ai/paper/2104.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00743"}},"official":{"repos":["allenai/gpv-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-generation-of-contrast-sets-from","slug":"automatic-generation-of-contrast-sets-from","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","date":"2021-03-17","arxiv_id":"2103.09591","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/automatic-generation-of-contrast-sets-from#ran","syntology_url":"https://syntology.ai/paper/2103.09591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09591"}},"official":{"repos":["yonatanbitton/AutoGenOfContrastSetsFromSceneGraphs"],"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/hurdles-to-progress-in-long-form-question","slug":"hurdles-to-progress-in-long-form-question","title":"Hurdles to Progress in Long-form Question Answering","date":"2021-03-10","arxiv_id":"2103.06332","repositories_listed":2,"syntology":null},{"url":"/paper/slake-a-semantically-labeled-knowledge","slug":"slake-a-semantically-labeled-knowledge","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","date":"2021-02-18","arxiv_id":"2102.09542","repositories_listed":2,"syntology":null},{"url":"/paper/noiseqa-challenge-set-evaluation-for-user","slug":"noiseqa-challenge-set-evaluation-for-user","title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering","date":"2021-02-16","arxiv_id":"2102.08345","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","repositories_listed":2,"syntology":null},{"url":"/paper/baleen-robust-multi-hop-reasoning-at-scale","slug":"baleen-robust-multi-hop-reasoning-at-scale","title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","date":"2021-01-02","arxiv_id":"2101.00436","repositories_listed":2,"syntology":null},{"url":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-doc-the-retrospective-long-document","slug":"ernie-doc-the-retrospective-long-document","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","date":"2020-12-31","arxiv_id":"2012.15688","repositories_listed":2,"syntology":null},{"url":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","repositories_listed":2,"syntology":null},{"url":"/paper/clinical-temporal-relation-extraction-with","slug":"clinical-temporal-relation-extraction-with","title":"Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference","date":"2020-12-16","arxiv_id":"2012.08790","repositories_listed":2,"syntology":null},{"url":"/paper/fusing-context-into-knowledge-graph-for","slug":"fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","repositories_listed":2,"syntology":null},{"url":"/paper/using-the-poly-encoder-for-a-covid-19","slug":"using-the-poly-encoder-for-a-covid-19","title":"Using the Poly-encoder for a COVID-19 Question Answering System","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/ffci-a-framework-for-interpretable-automatic","slug":"ffci-a-framework-for-interpretable-automatic","title":"FFCI: A Framework for Interpretable Automatic Evaluation of Summarization","date":"2020-11-27","arxiv_id":"2011.13662","repositories_listed":2,"syntology":null},{"url":"/paper/easytransfer-a-simple-and-scalable-deep","slug":"easytransfer-a-simple-and-scalable-deep","title":"EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications","date":"2020-11-18","arxiv_id":"2011.09463","repositories_listed":2,"syntology":null},{"url":"/paper/exams-a-multi-subject-high-school","slug":"exams-a-multi-subject-high-school","title":"EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering","date":"2020-11-05","arxiv_id":"2011.03080","repositories_listed":2,"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/exams-a-multi-subject-high-school#ran","syntology_url":"https://syntology.ai/paper/2011.03080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.03080"}},"official":{"repos":["mhardalov/exams-qa"],"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/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/cliniqg4qa-generating-diverse-questions-for","slug":"cliniqg4qa-generating-diverse-questions-for","title":"CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering","date":"2020-10-30","arxiv_id":"2010.16021","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cliniqg4qa-generating-diverse-questions-for#ran","syntology_url":"https://syntology.ai/paper/2010.16021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.16021"}},"official":{"repos":["panushri25/emrQA","sunlab-osu/CliniQG4QA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/russiansuperglue-a-russian-language","slug":"russiansuperglue-a-russian-language","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","date":"2020-10-29","arxiv_id":"2010.15925","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/russiansuperglue-a-russian-language#ran","syntology_url":"https://syntology.ai/paper/2010.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15925"}},"official":{"repos":["RussianNLP/RussianSuperGLUE"],"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/hierarchical-transformer-for-task-oriented","slug":"hierarchical-transformer-for-task-oriented","title":"Hierarchical Transformer for Task Oriented Dialog Systems","date":"2020-10-24","arxiv_id":"2011.08067","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-sequence-to-sequence-models-for","slug":"exploring-sequence-to-sequence-models-for","title":"Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition","date":"2020-10-21","arxiv_id":"2010.10900","repositories_listed":2,"syntology":null},{"url":"/paper/open-domain-question-answering-goes","slug":"open-domain-question-answering-goes","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","date":"2020-10-10","arxiv_id":"2010.04898","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/open-domain-question-answering-goes#ran","syntology_url":"https://syntology.ai/paper/2010.04898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04898"}},"official":{"repos":["apple/ml-qrecc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/infobert-improving-robustness-of-language-1","slug":"infobert-improving-robustness-of-language-1","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","date":"2020-10-05","arxiv_id":"2010.02329","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infobert-improving-robustness-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2010.02329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02329"}},"official":{"repos":["AI-secure/InfoBERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autoregressive-entity-retrieval","slug":"autoregressive-entity-retrieval","title":"Autoregressive Entity Retrieval","date":"2020-10-02","arxiv_id":"2010.00904","repositories_listed":2,"syntology":null},{"url":"/paper/liveqa-a-question-answering-dataset-over","slug":"liveqa-a-question-answering-dataset-over","title":"LiveQA: A Question Answering Dataset over Sports Live","date":"2020-10-01","arxiv_id":"2010.00526","repositories_listed":2,"syntology":null},{"url":"/paper/towards-question-answering-as-an-automatic","slug":"towards-question-answering-as-an-automatic","title":"Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary","date":"2020-10-01","arxiv_id":"2010.00490","repositories_listed":2,"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":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-question-answering-as-an-automatic#ran","syntology_url":"https://syntology.ai/paper/2010.00490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00490"}},"official":{"repos":["CogComp/qaeval-experiments"],"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","unlocated"]}}},{"url":"/paper/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/x-lxmert-paint-caption-and-answer-questions#ran","syntology_url":"https://syntology.ai/paper/2009.11278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11278"}},"official":{"repos":["allenai/x-lxmert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mutant-a-training-paradigm-for-out-of","slug":"mutant-a-training-paradigm-for-out-of","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","date":"2020-09-18","arxiv_id":"2009.08566","repositories_listed":2,"syntology":null},{"url":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","repositories_listed":2,"syntology":null},{"url":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","repositories_listed":2,"syntology":null},{"url":"/paper/mkqa-a-linguistically-diverse-benchmark-for","slug":"mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","arxiv_id":"2007.15207","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/mkqa-a-linguistically-diverse-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2007.15207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15207"}},"official":{"repos":["apple/ml-mkqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/advances-of-transformer-based-models-for-news","slug":"advances-of-transformer-based-models-for-news","title":"Advances of Transformer-Based Models for News Headline Generation","date":"2020-07-09","arxiv_id":"2007.05044","repositories_listed":2,"syntology":null},{"url":"/paper/kqa-pro-a-large-diagnostic-dataset-for","slug":"kqa-pro-a-large-diagnostic-dataset-for","title":"KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base","date":"2020-07-08","arxiv_id":"2007.03875","repositories_listed":2,"syntology":{"n":10,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":9,"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) · 9 unverified","sample_list":"/paper/kqa-pro-a-large-diagnostic-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2007.03875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03875"}},"official":{"repos":["shijx12/kqapro_baselines"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-multi-hop-question-answering-over","slug":"improving-multi-hop-question-answering-over","title":"Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/transferability-of-natural-language-inference","slug":"transferability-of-natural-language-inference","title":"Transferability of Natural Language Inference to Biomedical Question Answering","date":"2020-07-01","arxiv_id":"2007.00217","repositories_listed":2,"syntology":null},{"url":"/paper/multi-partition-embedding-interaction-with","slug":"multi-partition-embedding-interaction-with","title":"Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion","date":"2020-06-29","arxiv_id":"2006.16365","repositories_listed":2,"syntology":null},{"url":"/paper/selective-question-answering-under-domain","slug":"selective-question-answering-under-domain","title":"Selective Question Answering under Domain Shift","date":"2020-06-16","arxiv_id":"2006.09462","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":9,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}},"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/foreshadowing-the-benefits-of-incidental","slug":"foreshadowing-the-benefits-of-incidental","title":"Foreseeing the Benefits of Incidental Supervision","date":"2020-06-09","arxiv_id":"2006.05500","repositories_listed":2,"syntology":null},{"url":"/paper/bert-based-multilingual-machine-comprehension","slug":"bert-based-multilingual-machine-comprehension","title":"BERT Based Multilingual Machine Comprehension in English and Hindi","date":"2020-06-02","arxiv_id":"2006.01432","repositories_listed":2,"syntology":null},{"url":"/paper/structured-multimodal-attentions-for-textvqa","slug":"structured-multimodal-attentions-for-textvqa","title":"Structured Multimodal Attentions for TextVQA","date":"2020-06-01","arxiv_id":"2006.00753","repositories_listed":2,"syntology":null},{"url":"/paper/entity-enriched-neural-models-for-clinical","slug":"entity-enriched-neural-models-for-clinical","title":"Entity-Enriched Neural Models for Clinical Question Answering","date":"2020-05-13","arxiv_id":"2005.06587","repositories_listed":2,"syntology":null},{"url":"/paper/feqa-a-question-answering-evaluation","slug":"feqa-a-question-answering-evaluation","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","date":"2020-05-07","arxiv_id":"2005.03754","repositories_listed":2,"syntology":null},{"url":"/paper/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}},"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"14d247017b7f34efba9a0ea45009f21b6f3558d3f98117c092c09736555f58a6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}