DMCA
Unsupervised induction of semantic roles within a reconstructionerror minimization framework (2015)
| Venue: | In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| Citations: | 1 - 0 self |
BibTeX
@INPROCEEDINGS{Titov15unsupervisedinduction,
author = {Ivan Titov and Ehsan Khoddam},
title = {Unsupervised induction of semantic roles within a reconstructionerror minimization framework},
booktitle = {In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year = {2015},
pages = {1--10}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We introduce a new approach to unsupervised estimation of feature-rich semantic role la-beling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexi-cal features; (2) a reconstruction component: a tensor factorization model which relies on roles to predict argument fillers. When the components are estimated jointly to minimize errors in argument reconstruction, the induced roles largely correspond to roles defined in an-notated resources. Our method performs on par with most accurate role induction methods on English and German, even though, unlike these previous approaches, we do not incorpo-rate any prior linguistic knowledge about the languages. 1
Keyphrases
semantic role reconstructionerror minimization framework induced role argument filler prior linguistic knowledge tensor factorization model method performs an-notated resource new approach previous approach argument reconstruction encoding component lexi-cal feature unsupervised estimation accurate role induction method feature-rich semantic role la-beling model rich set reconstruction component
