Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework

Ivan Titov, Ehsan Khoddam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling 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 lexical 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 annotated 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 incorporate any prior linguistic knowledge about the
languages.
Original languageEnglish
Title of host publicationHuman Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL
PublisherAssociation for Computational Linguistics
Pages1-10
Number of pages10
ISBN (Print)978-1-941643-49-5
Publication statusPublished - Jun 2015

Fingerprint

Dive into the research topics of 'Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework'. Together they form a unique fingerprint.

Cite this