{"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/team-papelo-transformer-networks-at-fever","title":"Team Papelo: Transformer Networks at FEVER","arxiv_id":"1901.02534","date":"2019-01-08","proceeding":"WS 2018 11","authors":["Christopher Malon"],"abstract":"We develop a system for the FEVER fact extraction and verification challenge\nthat uses a high precision entailment classifier based on transformer networks\npretrained with language modeling, to classify a broad set of potential\nevidence. The precision of the entailment classifier allows us to enhance\nrecall by considering every statement from several articles to decide upon each\nclaim. We include not only the articles best matching the claim text by TFIDF\nscore, but read additional articles whose titles match named entities and\ncapitalized expressions occurring in the claim text. The entailment module\nevaluates potential evidence one statement at a time, together with the title\nof the page the evidence came from (providing a hint about possible pronoun\nantecedents). In preliminary evaluation, the system achieves .5736 FEVER score,\n.6108 label accuracy, and .6485 evidence F1 on the FEVER shared task test set.","url_abs":"http://arxiv.org/abs/1901.02534v1","url_pdf":"http://arxiv.org/pdf/1901.02534v1.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":"team-papelo-transformer-networks-at-fever","repo_url":"https://github.com/cdmalon/finetune-transformer-lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.02534","atlas_url":"https://app.syntology.ai/?focus=1901.02534","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}