Abstract | ||
---|---|---|
There has been an increasing attention to the task of fact checking. Among others, FEVER is a recently popular fact verification task in which a system is supposed to extract information from given Wikipedia documents and verify the given claim. In this paper, we present a four-stage model for this task including document retrieval, sentence selection, evidence sufficiency judgement and claim verification. Different from most existing models, we design a new evidence sufficiency judgement model to judge the sufficiency of the evidences for each claim and control the number of evidences dynamically. Experiments on FEVER show that our model is effective in judging the sufficiency of the evidence set and can get a better evidence F1 score with a comparable claim verification performance. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-32233-5_17 | Lecture Notes in Artificial Intelligence |
Keywords | DocType | Volume |
Claim verification,Fact checking,Natural language inference | Conference | 11838 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Lin | 1 | 0 | 0.34 |
Pengyu Huang | 2 | 0 | 0.34 |
Yuxuan Lai | 3 | 2 | 2.39 |
Yansong Feng | 4 | 735 | 64.17 |
Dongyan Zhao | 5 | 998 | 96.35 |