Saved in:
Bibliographic Details
Main Authors: Li, Xiangci, Burns, Gully, Peng, Nanyun
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2012.14500
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912377876774912
author Li, Xiangci
Burns, Gully
Peng, Nanyun
author_facet Li, Xiangci
Burns, Gully
Peng, Nanyun
contents Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales. The situation worsens as misinformation is proliferated on social media or news websites, manually or programmatically, at every moment. As a result, an automatic fact-verification tool becomes crucial for combating the spread of misinformation. In this work, we propose a novel, paragraph-level, multi-task learning model for the SciFact task by directly computing a sequence of contextualized sentence embeddings from a BERT model and jointly training the model on rationale selection and stance prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2012_14500
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
Li, Xiangci
Burns, Gully
Peng, Nanyun
Computation and Language
Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales. The situation worsens as misinformation is proliferated on social media or news websites, manually or programmatically, at every moment. As a result, an automatic fact-verification tool becomes crucial for combating the spread of misinformation. In this work, we propose a novel, paragraph-level, multi-task learning model for the SciFact task by directly computing a sequence of contextualized sentence embeddings from a BERT model and jointly training the model on rationale selection and stance prediction.
title A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
topic Computation and Language
url https://arxiv.org/abs/2012.14500