Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations

Ivan Titov, Ehsan Khoddam

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

Abstract / Description of output

In this work, we propose a new method to integrate two recent lines of work: unsupervised induction of shallow semantics (e.g., semantic roles) and factorization of relations in text and knowledge bases. 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, even though, unlike these previous approaches, we do not incorporate any prior linguistic knowledge about the language.
Original languageEnglish
Title of host publicationInternational Conference for Learning Representations (workshop track)
Number of pages5
Publication statusPublished - 2015

Fingerprint

Dive into the research topics of 'Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations'. Together they form a unique fingerprint.

Cite this