SURFACE: Semantically Rich Fact Validation with Explanations

Thumbnail Image

Files

1810.13223.pdf (593.08 KB)

Links to Files

https://arxiv.org/abs/1810.13223

Permanent Link

http://hdl.handle.net/11603/19227

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2018-10-31

Type of Work

conference papers and proceedings preprints
Text

Department

Program

Citation of Original Publication

Ankur Padia, Francis Ferraro and Tim Finin, SURFACE: Semantically Rich Fact Validation with Explanations, https://arxiv.org/abs/1810.13223

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution-NonCommercial-ShareAlike 4.0 International

Subjects

UMBC Ebiquity Research Group

Abstract

Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions. The recent FEVER task asked participants to classify input sentences as either SUPPORTED, REFUTED or NotEnoughInfo using Wikipedia as a source of true facts. SURFACE does this task and explains its decision through a selection of sentences from the trusted source. Our multi-task neural approach uses semantic lexical frames from FrameNet to jointly (i) find relevant evidential sentences in the trusted source and (ii) use them to classify the input sentence's veracity. An evaluation of our efficient three-parameter model on the FEVER dataset showed an improvement of 90% over the state-of-the-art baseline on retrieving relevant sentences and a 70% relative improvement in classification.