Neural models of factuality release_hisryuisk5ar7hmzewmn7jrocy

by Rachel Rudinger, Aaron Steven White, Benjamin Van Durme

Released as a article .

2018  

Abstract

We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME. We also present a substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset, yielding the largest event factuality dataset to date. We report model results on this extended factuality dataset as well.
In text/plain format

Archived Files and Locations

application/pdf  353.1 kB
file_5dnjxu6tsvhm7oeklz6u4lscjm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-04-06
Version   v1
Language   en ?
arXiv  1804.02472v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: dcf6cc84-be26-4193-be2c-d59e2aaad596
API URL: JSON