{"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/neural-network-models-for-paraphrase","title":"Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering","arxiv_id":"1806.04330","date":"2018-06-12","proceeding":"COLING 2018 8","authors":["Wuwei Lan","Wei Xu"],"abstract":"In this paper, we analyze several neural network designs (and their\nvariations) for sentence pair modeling and compare their performance\nextensively across eight datasets, including paraphrase identification,\nsemantic textual similarity, natural language inference, and question answering\ntasks. Although most of these models have claimed state-of-the-art performance,\nthe original papers often reported on only one or two selected datasets. We\nprovide a systematic study and show that (i) encoding contextual information by\nLSTM and inter-sentence interactions are critical, (ii) Tree-LSTM does not help\nas much as previously claimed but surprisingly improves performance on Twitter\ndatasets, (iii) the Enhanced Sequential Inference Model is the best so far for\nlarger datasets, while the Pairwise Word Interaction Model achieves the best\nperformance when less data is available. We release our implementations as an\nopen-source toolkit.","url_abs":"http://arxiv.org/abs/1806.04330v2","url_pdf":"http://arxiv.org/pdf/1806.04330v2.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":"neural-network-models-for-paraphrase","repo_url":"https://github.com/lanwuwei/SPM_toolkit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-pair-modeling","task_name":"Sentence Pair Modeling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/paraphrase-identification-on-2017-test-set","task":"Paraphrase Identification","dataset":"2017_test set","model":"CNN","rank_in_archive_order":1,"of":1,"metrics":{"10 fold Cross validation":"50"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04330"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/lanwuwei/SPM_toolkit","reach":null}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"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":2,"samples":[{"code_sha256_prefix":"1a3be51adc82197e","entry":"prepare_data","repo":"lanwuwei/SPM_toolkit","repo_kind":"official","path":"DecAtt/main_mnli.py","file_url":"https://github.com/lanwuwei/SPM_toolkit/blob/HEAD/DecAtt/main_mnli.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a3be51adc82197e"}},{"code_sha256_prefix":"2468a208d1b1a074","entry":"create_batch","repo":"lanwuwei/SPM_toolkit","repo_kind":"official","path":"DecAtt/main_mnli.py","file_url":"https://github.com/lanwuwei/SPM_toolkit/blob/HEAD/DecAtt/main_mnli.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2468a208d1b1a074"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}