{"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/3","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":3,"pages_in_order":109,"rows_per_page":100,"rows":[201,300],"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/2","next":"/task/question-answering/papers/4","papers":[{"url":"/paper/hungry-hungry-hippos-towards-language","slug":"hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","repositories_listed":3,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}},"official":{"repos":["hazyresearch/h3"],"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":["listed","official"]}}},{"url":"/paper/from-images-to-textual-prompts-zero-shot-vqa","slug":"from-images-to-textual-prompts-zero-shot-vqa","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","date":"2022-12-21","arxiv_id":"2212.10846","repositories_listed":3,"syntology":null},{"url":"/paper/query-enhanced-knowledge-intensive","slug":"query-enhanced-knowledge-intensive","title":"Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling","date":"2022-12-19","arxiv_id":"2212.09588","repositories_listed":3,"syntology":null},{"url":"/paper/apollo-an-optimized-training-approach-for","slug":"apollo-an-optimized-training-approach-for","title":"APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning","date":"2022-12-14","arxiv_id":"2212.07249","repositories_listed":3,"syntology":null},{"url":"/paper/holistic-evaluation-of-language-models","slug":"holistic-evaluation-of-language-models","title":"Holistic Evaluation of Language Models","date":"2022-11-16","arxiv_id":"2211.09110","repositories_listed":3,"syntology":null},{"url":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","slug":"plug-and-play-vqa-zero-shot-vqa-by-conjoining","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","date":"2022-10-17","arxiv_id":"2210.08773","repositories_listed":3,"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":3,"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/plug-and-play-vqa-zero-shot-vqa-by-conjoining#ran","syntology_url":"https://syntology.ai/paper/2210.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08773"}},"official":{"repos":["salesforce/lavis"],"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/ask-me-anything-a-simple-strategy-for","slug":"ask-me-anything-a-simple-strategy-for","title":"Ask Me Anything: A simple strategy for prompting language models","date":"2022-10-05","arxiv_id":"2210.02441","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ask-me-anything-a-simple-strategy-for#ran","syntology_url":"https://syntology.ai/paper/2210.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02441"}},"official":{"repos":["hazyresearch/ama_prompting"],"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":["official"]}}},{"url":"/paper/russian-web-tables-a-public-corpus-of-web","slug":"russian-web-tables-a-public-corpus-of-web","title":"Russian Web Tables: A Public Corpus of Web Tables for Russian Language Based on Wikipedia","date":"2022-10-03","arxiv_id":"2210.06353","repositories_listed":3,"syntology":null},{"url":"/paper/tvlt-textless-vision-language-transformer","slug":"tvlt-textless-vision-language-transformer","title":"TVLT: Textless Vision-Language Transformer","date":"2022-09-28","arxiv_id":"2209.14156","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"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 2 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/tvlt-textless-vision-language-transformer#ran","syntology_url":"https://syntology.ai/paper/2209.14156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14156"}},"official":{"repos":["zinengtang/tvlt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/step-by-step-a-hierarchical-framework-for","slug":"step-by-step-a-hierarchical-framework-for","title":"Step by step: a hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning","date":"2022-07-19","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/surgical-vqa-visual-question-answering-in","slug":"surgical-vqa-visual-question-answering-in","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","date":"2022-06-22","arxiv_id":"2206.11053","repositories_listed":3,"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":2,"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/surgical-vqa-visual-question-answering-in#ran","syntology_url":"https://syntology.ai/paper/2206.11053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11053"}},"official":{"repos":["lalithjets/surgical_vqa"],"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/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","repositories_listed":3,"syntology":{"n":34,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":20,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}},"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]}}},{"url":"/paper/zusammenqa-data-augmentation-with-specialized","slug":"zusammenqa-data-augmentation-with-specialized","title":"ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System","date":"2022-05-30","arxiv_id":"2205.14981","repositories_listed":3,"syntology":null},{"url":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/metgen-a-module-based-entailment-tree","slug":"metgen-a-module-based-entailment-tree","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","date":"2022-05-05","arxiv_id":"2205.02593","repositories_listed":3,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/metgen-a-module-based-entailment-tree#ran","syntology_url":"https://syntology.ai/paper/2205.02593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02593"}},"official":{"repos":["Raising-hrx/MetGen"],"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/it5-large-scale-text-to-text-pretraining-for","slug":"it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","repositories_listed":3,"syntology":null},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"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/zerogen-efficient-zero-shot-learning-via","slug":"zerogen-efficient-zero-shot-learning-via","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","date":"2022-02-16","arxiv_id":"2202.07922","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"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) · 4 unverified","sample_list":"/paper/zerogen-efficient-zero-shot-learning-via#ran","syntology_url":"https://syntology.ai/paper/2202.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.07922"}},"official":{"repos":["HKUNLP/zerogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/iglue-a-benchmark-for-transfer-learning","slug":"iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","date":"2022-01-27","arxiv_id":"2201.11732","repositories_listed":3,"syntology":{"n":21,"n_ran":17,"n_constructed":2,"n_ran_checked":11,"n_instrument":6,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/iglue-a-benchmark-for-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/2201.11732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11732"}},"official":{"repos":["e-bug/iglue","e-bug/volta"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/table-pretraining-a-survey-on-model","slug":"table-pretraining-a-survey-on-model","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","date":"2022-01-24","arxiv_id":"2201.09745","repositories_listed":3,"syntology":null},{"url":"/paper/quality-question-answering-with-long-input","slug":"quality-question-answering-with-long-input","title":"QuALITY: Question Answering with Long Input Texts, Yes!","date":"2021-12-16","arxiv_id":"2112.08608","repositories_listed":3,"syntology":null},{"url":"/paper/tempoqr-temporal-question-reasoning-over","slug":"tempoqr-temporal-question-reasoning-over","title":"TempoQR: Temporal Question Reasoning over Knowledge Graphs","date":"2021-12-10","arxiv_id":"2112.05785","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/debertav3-improving-deberta-using-electra#ran","syntology_url":"https://syntology.ai/paper/2111.09543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09543"}},"official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/perceptual-score-what-data-modalities-does","slug":"perceptual-score-what-data-modalities-does","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","date":"2021-10-27","arxiv_id":"2110.14375","repositories_listed":3,"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/perceptual-score-what-data-modalities-does#ran","syntology_url":"https://syntology.ai/paper/2110.14375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14375"}},"official":{"repos":["itaigat/perceptual-score"],"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/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/truthfulqa-measuring-how-models-mimic-human#ran","syntology_url":"https://syntology.ai/paper/2109.07958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07958"}},"official":{"repos":["sylinrl/truthfulqa"],"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":["official"]}}},{"url":"/paper/webqa-multihop-and-multimodal-qa","slug":"webqa-multihop-and-multimodal-qa","title":"WebQA: Multihop and Multimodal QA","date":"2021-09-01","arxiv_id":"2109.00590","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/webqa-multihop-and-multimodal-qa#ran","syntology_url":"https://syntology.ai/paper/2109.00590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00590"}},"official":null}},{"url":"/paper/musique-multi-hop-questions-via-single-hop","slug":"musique-multi-hop-questions-via-single-hop","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","date":"2021-08-02","arxiv_id":"2108.00573","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/musique-multi-hop-questions-via-single-hop#ran","syntology_url":"https://syntology.ai/paper/2108.00573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00573"}},"official":{"repos":["stonybrooknlp/musique"],"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":["listed","official"]}}},{"url":"/paper/answer-complex-questions-path-ranker-is-all","slug":"answer-complex-questions-path-ranker-is-all","title":"Answer Complex Questions: Path Ranker Is All You Need","date":"2021-07-11","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/ethics-sheets-for-ai-tasks","slug":"ethics-sheets-for-ai-tasks","title":"Ethics Sheets for AI Tasks","date":"2021-07-02","arxiv_id":"2107.01183","repositories_listed":3,"syntology":null},{"url":"/paper/vogue-answer-verbalization-through-multi-task","slug":"vogue-answer-verbalization-through-multi-task","title":"VOGUE: Answer Verbalization through Multi-Task Learning","date":"2021-06-24","arxiv_id":"2106.13316","repositories_listed":3,"syntology":null},{"url":"/paper/narrative-question-answering-with-cutting","slug":"narrative-question-answering-with-cutting","title":"Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study","date":"2021-06-07","arxiv_id":"2106.03826","repositories_listed":3,"syntology":null},{"url":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}},"official":null}},{"url":"/paper/natural-instructions-benchmarking","slug":"natural-instructions-benchmarking","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","date":"2021-04-18","arxiv_id":"2104.08773","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/natural-instructions-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2104.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08773"}},"official":{"repos":["allenai/natural-instructions","allenai/natural-instructions-v1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","slug":"beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","date":"2021-04-17","arxiv_id":"2104.08663","repositories_listed":3,"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/beir-a-heterogenous-benchmark-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2104.08663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08663"}},"official":{"repos":["UKPLab/beir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/editing-factual-knowledge-in-language-models","slug":"editing-factual-knowledge-in-language-models","title":"Editing Factual Knowledge in Language Models","date":"2021-04-16","arxiv_id":"2104.08164","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/editing-factual-knowledge-in-language-models#ran","syntology_url":"https://syntology.ai/paper/2104.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08164"}},"official":{"repos":["nicola-decao/KnowledgeEditor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trafficqa-a-question-answering-benchmark-and","slug":"trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","date":"2021-03-29","arxiv_id":"2103.15538","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":1,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 1 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/trafficqa-a-question-answering-benchmark-and#ran","syntology_url":"https://syntology.ai/paper/2103.15538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15538"}},"official":{"repos":["SUTDCV/SUTD-TrafficQA"],"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/conceptual-12m-pushing-web-scale-image-text","slug":"conceptual-12m-pushing-web-scale-image-text","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","date":"2021-02-17","arxiv_id":"2102.08981","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-good-in-context-examples-for-gpt-3","slug":"what-makes-good-in-context-examples-for-gpt-3","title":"What Makes Good In-Context Examples for GPT-$3$?","date":"2021-01-17","arxiv_id":"2101.06804","repositories_listed":3,"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/what-makes-good-in-context-examples-for-gpt-3#ran","syntology_url":"https://syntology.ai/paper/2101.06804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06804"}},"official":null}},{"url":"/paper/lrta-a-transparent-neural-symbolic-reasoning","slug":"lrta-a-transparent-neural-symbolic-reasoning","title":"LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering","date":"2020-11-21","arxiv_id":"2011.10731","repositories_listed":3,"syntology":null},{"url":"/paper/xor-qa-cross-lingual-open-retrieval-question","slug":"xor-qa-cross-lingual-open-retrieval-question","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","date":"2020-10-22","arxiv_id":"2010.11856","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xor-qa-cross-lingual-open-retrieval-question#ran","syntology_url":"https://syntology.ai/paper/2010.11856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11856"}},"official":{"repos":["AkariAsai/XORQA"],"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/unsupervised-deep-learning-based-multiple","slug":"unsupervised-deep-learning-based-multiple","title":"Unsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge","date":"2020-10-21","arxiv_id":"2010.11003","repositories_listed":3,"syntology":null},{"url":"/paper/autoqa-from-databases-to-qa-semantic-parsers","slug":"autoqa-from-databases-to-qa-semantic-parsers","title":"AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data","date":"2020-10-09","arxiv_id":"2010.04806","repositories_listed":3,"syntology":{"n":26,"n_ran":13,"n_constructed":2,"n_ran_checked":10,"n_instrument":3,"n_unverified":13,"n_honours":1,"n_violates":4,"n_no_contract":5,"n_pointer_only":26,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 4 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/autoqa-from-databases-to-qa-semantic-parsers#ran","syntology_url":"https://syntology.ai/paper/2010.04806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04806"}},"official":{"repos":["stanford-oval/genienlp","stanford-oval/genie-toolkit","stanford-oval/schema2qa"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-one-pass-end-to-end-entity-linking","slug":"efficient-one-pass-end-to-end-entity-linking","title":"Efficient One-Pass End-to-End Entity Linking for Questions","date":"2020-10-06","arxiv_id":"2010.02413","repositories_listed":3,"syntology":null},{"url":"/paper/what-disease-does-this-patient-have-a-large","slug":"what-disease-does-this-patient-have-a-large","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","date":"2020-09-28","arxiv_id":"2009.13081","repositories_listed":3,"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/what-disease-does-this-patient-have-a-large#ran","syntology_url":"https://syntology.ai/paper/2009.13081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13081"}},"official":{"repos":["jind11/MedQA"],"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/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"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":1,"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/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}},"official":{"repos":["facebookresearch/KILT"],"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/hitter-hierarchical-transformers-for","slug":"hitter-hierarchical-transformers-for","title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","date":"2020-08-28","arxiv_id":"2008.12813","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/hitter-hierarchical-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2008.12813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.12813"}},"official":null}},{"url":"/paper/docvqa-a-dataset-for-vqa-on-document-images","slug":"docvqa-a-dataset-for-vqa-on-document-images","title":"DocVQA: A Dataset for VQA on Document Images","date":"2020-07-01","arxiv_id":"2007.00398","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/docvqa-a-dataset-for-vqa-on-document-images#ran","syntology_url":"https://syntology.ai/paper/2007.00398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00398"}},"official":null}},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mad-x-an-adapter-based-framework-for-multi","slug":"mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","repositories_listed":3,"syntology":null},{"url":"/paper/event-extraction-by-answering-almost-natural","slug":"event-extraction-by-answering-almost-natural","title":"Event Extraction by Answering (Almost) Natural Questions","date":"2020-04-28","arxiv_id":"2004.13625","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/event-extraction-by-answering-almost-natural#ran","syntology_url":"https://syntology.ai/paper/2004.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13625"}},"official":{"repos":["xinyadu/eeqa"],"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":["listed","official"]}}},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/schema2qa-answering-complex-queries-on-the","slug":"schema2qa-answering-complex-queries-on-the","title":"Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web","date":"2020-01-16","arxiv_id":"2001.05609","repositories_listed":3,"syntology":null},{"url":"/paper/advcodec-towards-a-unified-framework-for-1","slug":"advcodec-towards-a-unified-framework-for-1","title":"T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack","date":"2019-12-22","arxiv_id":"1912.10375","repositories_listed":3,"syntology":null},{"url":"/paper/measuring-compositional-generalization-a-1","slug":"measuring-compositional-generalization-a-1","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","date":"2019-12-20","arxiv_id":"1912.09713","repositories_listed":3,"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/measuring-compositional-generalization-a-1#ran","syntology_url":"https://syntology.ai/paper/1912.09713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09713"}},"official":{"repos":["google-research/google-research"],"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/differentiable-reasoning-on-large-knowledge","slug":"differentiable-reasoning-on-large-knowledge","title":"Differentiable Reasoning on Large Knowledge Bases and Natural Language","date":"2019-12-17","arxiv_id":"1912.10824","repositories_listed":3,"syntology":{"n":26,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/differentiable-reasoning-on-large-knowledge#ran","syntology_url":"https://syntology.ai/paper/1912.10824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10824"}},"official":{"repos":["uclnlp/gntp","uclnlp/ntp","uclnlp/ctp"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-spanish-translation-of-the-squad","slug":"automatic-spanish-translation-of-the-squad","title":"Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering","date":"2019-12-11","arxiv_id":"1912.05200","repositories_listed":3,"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/automatic-spanish-translation-of-the-squad#ran","syntology_url":"https://syntology.ai/paper/1912.05200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05200"}},"official":{"repos":["ccasimiro88/TranslateAlignRetrieve"],"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":["listed","official"]}}},{"url":"/paper/commongen-a-constrained-text-generation","slug":"commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","date":"2019-11-09","arxiv_id":"1911.03705","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/commongen-a-constrained-text-generation#ran","syntology_url":"https://syntology.ai/paper/1911.03705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03705"}},"official":null}},{"url":"/paper/contextualized-sparse-representation-with-1","slug":"contextualized-sparse-representation-with-1","title":"Contextualized Sparse Representations for Real-Time Open-Domain Question Answering","date":"2019-11-07","arxiv_id":"1911.02896","repositories_listed":3,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":6,"n_honours":5,"n_violates":2,"n_no_contract":2,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/contextualized-sparse-representation-with-1#ran","syntology_url":"https://syntology.ai/paper/1911.02896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02896"}},"official":{"repos":["jhyuklee/sparc"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/plato-pre-trained-dialogue-generation-model","slug":"plato-pre-trained-dialogue-generation-model","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","date":"2019-10-17","arxiv_id":"1910.07931","repositories_listed":3,"syntology":null},{"url":"/paper/enhancing-the-transformer-with-explicit-1","slug":"enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","date":"2019-10-15","arxiv_id":"1910.06611","repositories_listed":3,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-the-transformer-with-explicit-1#ran","syntology_url":"https://syntology.ai/paper/1910.06611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06611"}},"official":{"repos":["ischlag/TP-Transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-hop-question-answering-via-reasoning","slug":"multi-hop-question-answering-via-reasoning","title":"Multi-hop Question Answering via Reasoning Chains","date":"2019-10-07","arxiv_id":"1910.02610","repositories_listed":3,"syntology":null},{"url":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}},"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-trained-language-model-for-biomedical","slug":"pre-trained-language-model-for-biomedical","title":"Pre-trained Language Model for Biomedical Question Answering","date":"2019-09-18","arxiv_id":"1909.08229","repositories_listed":3,"syntology":null},{"url":"/paper/dont-take-the-easy-way-out-ensemble-based","slug":"dont-take-the-easy-way-out-ensemble-based","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","date":"2019-09-09","arxiv_id":"1909.03683","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dont-take-the-easy-way-out-ensemble-based#ran","syntology_url":"https://syntology.ai/paper/1909.03683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03683"}},"official":{"repos":["chrisc36/debias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/neural-attentive-bag-of-entities-model-for","slug":"neural-attentive-bag-of-entities-model-for","title":"Neural Attentive Bag-of-Entities Model for Text Classification","date":"2019-09-03","arxiv_id":"1909.01259","repositories_listed":3,"syntology":null},{"url":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"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/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}},"official":{"repos":["jackroos/VL-BERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/simple-and-effective-text-matching-with-1","slug":"simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","repositories_listed":3,"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":1,"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/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}},"official":{"repos":["hitvoice/RE2"],"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/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}},"official":{"repos":["PaddlePaddle/ERNIE"],"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/eli5-long-form-question-answering","slug":"eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","date":"2019-07-22","arxiv_id":"1907.09190","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eli5-long-form-question-answering#ran","syntology_url":"https://syntology.ai/paper/1907.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09190"}},"official":{"repos":["facebookresearch/ELI5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/190600300","slug":"190600300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","date":"2019-06-01","arxiv_id":"1906.00300","repositories_listed":3,"syntology":null},{"url":"/paper/opiec-an-open-information-extraction-corpus","slug":"opiec-an-open-information-extraction-corpus","title":"OPIEC: An Open Information Extraction Corpus","date":"2019-04-28","arxiv_id":"1904.12324","repositories_listed":3,"syntology":null},{"url":"/paper/tvqa-spatio-temporal-grounding-for-video","slug":"tvqa-spatio-temporal-grounding-for-video","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","date":"2019-04-25","arxiv_id":"1904.11574","repositories_listed":3,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tvqa-spatio-temporal-grounding-for-video#ran","syntology_url":"https://syntology.ai/paper/1904.11574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11574"}},"official":{"repos":["jayleicn/TVQA-PLUS","jayleicn/TVQAplus"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/drop-a-reading-comprehension-benchmark","slug":"drop-a-reading-comprehension-benchmark","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","date":"2019-03-01","arxiv_id":"1903.00161","repositories_listed":3,"syntology":null},{"url":"/paper/a-bert-baseline-for-the-natural-questions","slug":"a-bert-baseline-for-the-natural-questions","title":"A BERT Baseline for the Natural Questions","date":"2019-01-24","arxiv_id":"1901.08634","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"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, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-bert-baseline-for-the-natural-questions#ran","syntology_url":"https://syntology.ai/paper/1901.08634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08634"}},"official":{"repos":["google-research/language"],"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/a-question-entailment-approach-to-question","slug":"a-question-entailment-approach-to-question","title":"A Question-Entailment Approach to Question Answering","date":"2019-01-23","arxiv_id":"1901.08079","repositories_listed":3,"syntology":null},{"url":"/paper/clevr-ref-diagnosing-visual-reasoning-with","slug":"clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}},{"url":"/paper/no-one-is-perfect-analysing-the-performance","slug":"no-one-is-perfect-analysing-the-performance","title":"No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph","date":"2018-09-26","arxiv_id":"1809.10044","repositories_listed":3,"syntology":null},{"url":"/paper/emrqa-a-large-corpus-for-question-answering","slug":"emrqa-a-large-corpus-for-question-answering","title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","date":"2018-09-03","arxiv_id":"1809.00732","repositories_listed":3,"syntology":null},{"url":"/paper/evaluating-theory-of-mind-in-question","slug":"evaluating-theory-of-mind-in-question","title":"Evaluating Theory of Mind in Question Answering","date":"2018-08-28","arxiv_id":"1808.09352","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-attend-on-essential-terms-an","slug":"learning-to-attend-on-essential-terms-an","title":"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering","date":"2018-08-28","arxiv_id":"1808.09492","repositories_listed":3,"syntology":null},{"url":"/paper/spoken-squad-a-study-of-mitigating-the-impact","slug":"spoken-squad-a-study-of-mitigating-the-impact","title":"Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension","date":"2018-04-01","arxiv_id":"1804.00320","repositories_listed":3,"syntology":null},{"url":"/paper/attention-on-attention-architectures-for","slug":"attention-on-attention-architectures-for","title":"Attention on Attention: Architectures for Visual Question Answering (VQA)","date":"2018-03-21","arxiv_id":"1803.07724","repositories_listed":3,"syntology":null},{"url":"/paper/fact-checking-in-community-forums","slug":"fact-checking-in-community-forums","title":"Fact Checking in Community Forums","date":"2018-03-08","arxiv_id":"1803.03178","repositories_listed":3,"syntology":null},{"url":"/paper/a-deep-relevance-matching-model-for-ad-hoc","slug":"a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","arxiv_id":"1711.08611","repositories_listed":3,"syntology":null},{"url":"/paper/fusionnet-fusing-via-fully-aware-attention","slug":"fusionnet-fusing-via-fully-aware-attention","title":"FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension","date":"2017-11-16","arxiv_id":"1711.07341","repositories_listed":3,"syntology":null},{"url":"/paper/indirect-supervision-for-relation-extraction","slug":"indirect-supervision-for-relation-extraction","title":"Indirect Supervision for Relation Extraction using Question-Answer Pairs","date":"2017-10-30","arxiv_id":"1710.11169","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-rank-question-answer-pairs-using","slug":"learning-to-rank-question-answer-pairs-using","title":"Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering","date":"2017-10-10","arxiv_id":"1710.03430","repositories_listed":3,"syntology":null},{"url":"/paper/a-simple-loss-function-for-improving-the","slug":"a-simple-loss-function-for-improving-the","title":"A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models","date":"2017-08-02","arxiv_id":"1708.00584","repositories_listed":3,"syntology":null},{"url":"/paper/semeval-2017-task-1-semantic-textual","slug":"semeval-2017-task-1-semantic-textual","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","date":"2017-07-31","arxiv_id":"1708.00055","repositories_listed":3,"syntology":null},{"url":"/paper/adversarial-examples-for-evaluating-reading","slug":"adversarial-examples-for-evaluating-reading","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","date":"2017-07-23","arxiv_id":"1707.07328","repositories_listed":3,"syntology":null},{"url":"/paper/irgan-a-minimax-game-for-unifying-generative","slug":"irgan-a-minimax-game-for-unifying-generative","title":"IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models","date":"2017-05-30","arxiv_id":"1705.10513","repositories_listed":3,"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/irgan-a-minimax-game-for-unifying-generative#ran","syntology_url":"https://syntology.ai/paper/1705.10513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10513"}},"official":{"repos":["geek-ai/irgan"],"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/reinforced-mnemonic-reader-for-machine","slug":"reinforced-mnemonic-reader-for-machine","title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","date":"2017-05-08","arxiv_id":"1705.02798","repositories_listed":3,"syntology":null},{"url":"/paper/searchqa-a-new-qa-dataset-augmented-with","slug":"searchqa-a-new-qa-dataset-augmented-with","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","date":"2017-04-18","arxiv_id":"1704.05179","repositories_listed":3,"syntology":null},{"url":"/paper/making-neural-qa-as-simple-as-possible-but","slug":"making-neural-qa-as-simple-as-possible-but","title":"Making Neural QA as Simple as Possible but not Simpler","date":"2017-03-14","arxiv_id":"1703.04816","repositories_listed":3,"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":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) · 1 unverified","sample_list":"/paper/making-neural-qa-as-simple-as-possible-but#ran","syntology_url":"https://syntology.ai/paper/1703.04816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04816"}},"official":null}},{"url":"/paper/dataset-and-neural-recurrent-sequence","slug":"dataset-and-neural-recurrent-sequence","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","date":"2016-07-21","arxiv_id":"1607.06275","repositories_listed":3,"syntology":null},{"url":"/paper/neural-semantic-encoders","slug":"neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","arxiv_id":"1607.04315","repositories_listed":3,"syntology":null},{"url":"/paper/moving-beyond-the-turing-test-with-the-allen","slug":"moving-beyond-the-turing-test-with-the-allen","title":"Moving Beyond the Turing Test with the Allen AI Science Challenge","date":"2016-04-14","arxiv_id":"1604.04315","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-batch-normalization","slug":"recurrent-batch-normalization","title":"Recurrent Batch Normalization","date":"2016-03-30","arxiv_id":"1603.09025","repositories_listed":3,"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":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) · 1 unverified","sample_list":"/paper/recurrent-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/1603.09025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09025"}},"official":null}},{"url":"/paper/attentive-pooling-networks","slug":"attentive-pooling-networks","title":"Attentive Pooling Networks","date":"2016-02-11","arxiv_id":"1602.03609","repositories_listed":3,"syntology":null}],"record_sha256":"3e15d812be677259a1a0f8c122628d98bd199b984f0b6a1e944e6d89c42b9a13","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}