{"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/defactonlp-fact-verification-using-entity","title":"DeFactoNLP: Fact Verification using Entity Recognition, TFIDF Vector Comparison and Decomposable Attention","arxiv_id":"1809.00509","date":"2018-09-03","proceeding":"WS 2018 11","authors":["Aniketh Janardhan Reddy","Gil Rocha","Diego Esteves"],"abstract":"In this paper, we describe DeFactoNLP, the system we designed for the FEVER\n2018 Shared Task. The aim of this task was to conceive a system that can not\nonly automatically assess the veracity of a claim but also retrieve evidence\nsupporting this assessment from Wikipedia. In our approach, the Wikipedia\ndocuments whose Term Frequency-Inverse Document Frequency (TFIDF) vectors are\nmost similar to the vector of the claim and those documents whose names are\nsimilar to those of the named entities (NEs) mentioned in the claim are\nidentified as the documents which might contain evidence. The sentences in\nthese documents are then supplied to a textual entailment recognition module.\nThis module calculates the probability of each sentence supporting the claim,\ncontradicting the claim or not providing any relevant information to assess the\nveracity of the claim. Various features computed using these probabilities are\nfinally used by a Random Forest classifier to determine the overall\ntruthfulness of the claim. The sentences which support this classification are\nreturned as evidence. Our approach achieved a 0.4277 evidence F1-score, a\n0.5136 label accuracy and a 0.3833 FEVER score.","url_abs":"http://arxiv.org/abs/1809.00509v1","url_pdf":"http://arxiv.org/pdf/1809.00509v1.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":"defactonlp-fact-verification-using-entity","repo_url":"https://github.com/DeFacto/DeFactoNLP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"fact-verification","task_name":"Fact Verification"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00509","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}