{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/machine-comprehension-using-match-lstm-and","title":"Machine Comprehension Using Match-LSTM and Answer Pointer","arxiv_id":"1608.07905","date":"2016-08-29","proceeding":null,"authors":["Shuohang Wang","Jing Jiang"],"abstract":"Machine comprehension of text is an important problem in natural language\nprocessing. A recently released dataset, the Stanford Question Answering\nDataset (SQuAD), offers a large number of real questions and their answers\ncreated by humans through crowdsourcing. SQuAD provides a challenging testbed\nfor evaluating machine comprehension algorithms, partly because compared with\nprevious datasets, in SQuAD the answers do not come from a small set of\ncandidate answers and they have variable lengths. We propose an end-to-end\nneural architecture for the task. The architecture is based on match-LSTM, a\nmodel we proposed previously for textual entailment, and Pointer Net, a\nsequence-to-sequence model proposed by Vinyals et al.(2015) to constrain the\noutput tokens to be from the input sequences. We propose two ways of using\nPointer Net for our task. Our experiments show that both of our two models\nsubstantially outperform the best results obtained by Rajpurkar et al.(2016)\nusing logistic regression and manually crafted features.","url_abs":"http://arxiv.org/abs/1608.07905v2","url_pdf":"http://arxiv.org/pdf/1608.07905v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"machine-comprehension-using-match-lstm-and","repo_url":"https://github.com/shuohangwang/SeqMatchSeq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"machine-comprehension-using-match-lstm-and","repo_url":"https://github.com/HKUST-KnowComp/MnemonicReader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"machine-comprehension-using-match-lstm-and","repo_url":"https://github.com/HKUST-KnowComp/R-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"machine-comprehension-using-match-lstm-and","repo_url":"https://github.com/baidu/DuReader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"machine-comprehension-using-match-lstm-and","repo_url":"https://github.com/geraltofrivia/match-lstm-ptr-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Unlicense"}}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[{"method_slug":"logistic-regression","method_name":"Logistic Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Match-LSTM with Ans-Ptr (Boundary) (ensemble)","rank_in_archive_order":171,"of":213,"metrics":{"EM":"67.901","F1":"77.022"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Match-LSTM with Bi-Ans-Ptr (Boundary)","rank_in_archive_order":181,"of":213,"metrics":{"EM":"64.744","F1":"73.743"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Match-LSTM with Ans-Ptr (Boundary)","rank_in_archive_order":191,"of":213,"metrics":{"EM":"60.474","F1":"70.695"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Match-LSTM with Ans-Ptr (Sentence)","rank_in_archive_order":195,"of":213,"metrics":{"EM":"54.505","F1":"67.748"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"Match-LSTM with Bi-Ans-Ptr (Boundary+Search+b)","rank_in_archive_order":47,"of":55,"metrics":{"EM":"64.1","F1":" 64.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.07905","atlas_url":"https://app.syntology.ai/?focus=1608.07905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.07905"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuohangwang/SeqMatchSeq","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HKUST-KnowComp/R-Net","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HKUST-KnowComp/MnemonicReader","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baidu/DuReader","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/geraltofrivia/match-lstm-ptr-network","reach":{"status":"ok","spdx":"Unlicense"}}],"summary":{"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"f6c275d6a18330a9","entry":"exact_match_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f6c275d6a18330a9"}},{"code_sha256_prefix":"2112c433b9c6d343","entry":"f1_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2112c433b9c6d343"}},{"code_sha256_prefix":"c6a80c065d2e4851","entry":"normalize_answer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c6a80c065d2e4851"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}