{"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/combining-fact-extraction-and-verification","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","arxiv_id":"1811.07039","date":"2018-11-16","proceeding":null,"authors":["Yixin Nie","Haonan Chen","Mohit Bansal"],"abstract":"The increasing concern with misinformation has stimulated research efforts on\nautomatic fact checking. The recently-released FEVER dataset introduced a\nbenchmark fact-verification task in which a system is asked to verify a claim\nusing evidential sentences from Wikipedia documents. In this paper, we present\na connected system consisting of three homogeneous neural semantic matching\nmodels that conduct document retrieval, sentence selection, and claim\nverification jointly for fact extraction and verification. For evidence\nretrieval (document retrieval and sentence selection), unlike traditional\nvector space IR models in which queries and sources are matched in some\npre-designed term vector space, we develop neural models to perform deep\nsemantic matching from raw textual input, assuming no intermediate term\nrepresentation and no access to structured external knowledge bases. We also\nshow that Pageview frequency can also help improve the performance of evidence\nretrieval results, that later can be matched by using our neural semantic\nmatching network. For claim verification, unlike previous approaches that\nsimply feed upstream retrieved evidence and the claim to a natural language\ninference (NLI) model, we further enhance the NLI model by providing it with\ninternal semantic relatedness scores (hence integrating it with the evidence\nretrieval modules) and ontological WordNet features. Experiments on the FEVER\ndataset indicate that (1) our neural semantic matching method outperforms\npopular TF-IDF and encoder models, by significant margins on all evidence\nretrieval metrics, (2) the additional relatedness score and WordNet features\nimprove the NLI model via better semantic awareness, and (3) by formalizing all\nthree subtasks as a similar semantic matching problem and improving on all\nthree stages, the complete model is able to achieve the state-of-the-art\nresults on the FEVER test set.","url_abs":"http://arxiv.org/abs/1811.07039v1","url_pdf":"http://arxiv.org/pdf/1811.07039v1.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":"combining-fact-extraction-and-verification","repo_url":"https://github.com/easonnie/combine-FEVER-NSMN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"combining-fact-extraction-and-verification","repo_url":"https://github.com/ShyamSubramanian/HESM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"claim-verification","task_name":"Claim Verification"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"fact-verification","task_name":"Fact Verification"},{"task_slug":"misinformation","task_name":"Misinformation"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.07039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07039"}},"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/ShyamSubramanian/HESM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/easonnie/combine-FEVER-NSMN","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":1,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"75be915616e6844d","entry":"eval_model","repo":"easonnie/combine-FEVER-NSMN","repo_kind":"official","path":"src/nli/mesim_wn_simi_v1_3.py","file_url":"https://github.com/easonnie/combine-FEVER-NSMN/blob/HEAD/src/nli/mesim_wn_simi_v1_3.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75be915616e6844d"}},{"code_sha256_prefix":"1039f6e2c844fd60","entry":"get_sampled_data","repo":"easonnie/combine-FEVER-NSMN","repo_kind":"official","path":"src/nli/mesim_wn_simi_v1_3.py","file_url":"https://github.com/easonnie/combine-FEVER-NSMN/blob/HEAD/src/nli/mesim_wn_simi_v1_3.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1039f6e2c844fd60"}},{"code_sha256_prefix":"371411805502aad4","entry":"merge_nli_results","repo":"easonnie/combine-FEVER-NSMN","repo_kind":"official","path":"src/pipeline/auto_pipeline.py","file_url":"https://github.com/easonnie/combine-FEVER-NSMN/blob/HEAD/src/pipeline/auto_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"371411805502aad4"}},{"code_sha256_prefix":"a3d6db7060e3abbb","entry":"merge_sent_results","repo":"easonnie/combine-FEVER-NSMN","repo_kind":"official","path":"src/pipeline/auto_pipeline.py","file_url":"https://github.com/easonnie/combine-FEVER-NSMN/blob/HEAD/src/pipeline/auto_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3d6db7060e3abbb"}},{"code_sha256_prefix":"08ddede5a1a67a1f","entry":"norm_weight","repo":"ShyamSubramanian/HESM","repo_kind":"listed","path":"src/nli/hesm_fever.py","file_url":"https://github.com/ShyamSubramanian/HESM/blob/HEAD/src/nli/hesm_fever.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08ddede5a1a67a1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}