论文信息 - Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification.

Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification.

This paper presents the ColumbiaNLP submission for the FEVER Workshop Shared Task. Our system is an end-to-end pipeline that extracts factual evidence from Wikipedia and infers a decision about the truthfulness of the claim based on the extracted evidence. Our pipeline achieves significant improvement over the baseline for all the components (Document Retrieval, Sentence Selection and Textual Entailment) both on the development set and the test set. Our team finished 6th out of 24 teams on the leader-board based on the preliminary results with a FEVER score of 49.06 on the blind test set compared to 27.45 of the baseline system.

[1] Andreas Vlachos,et al. FEVER: a Large-scale Dataset for Fact Extraction and VERification , 2018, NAACL.

[2] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.

[3] Xuezhi Wang,et al. Relevant Document Discovery for Fact-Checking Articles , 2018, WWW.

[4] Jakob Uszkoreit,et al. A Decomposable Attention Model for Natural Language Inference , 2016, EMNLP.

[5] Chandra Bhagavatula,et al. Semi-supervised sequence tagging with bidirectional language models , 2017, ACL.

[6] Luke S. Zettlemoyer,et al. AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[7] Luke S. Zettlemoyer,et al. Deep Contextualized Word Representations , 2018, NAACL.

[8] Tomas Mikolov,et al. Enriching Word Vectors with Subword Information , 2016, TACL.

[9] Jason Weston,et al. Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.

[10] Holger Schwenk,et al. Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.