Abstract
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.
Highlights
Shallow semantic representations, and semantic role labels in particular, have a long history in linguistics (Fillmore, 1968)
Semantic role representations encode the underlying predicate-argument structure of sentences, or, for every predicate in a sentence they identify a set of arguments and associate each argument with an underlying semantic role, such as an agent or a patient
This work introduces a method for inducing featurerich semantic role labelers from unannoated text
Summary
Semantic role labels in particular, have a long history in linguistics (Fillmore, 1968). Most current statistical approaches to SRL are supervised, requiring large quantities of human annotated data to estimate model parameters. Such resources are expensive to create and only available for a small number of languages. Unlike state-ofthe-art supervised parsers, they rely on a very simplistic set of features of a sentence. These factors lead to models being insufficiently expressive to capture the syntax-semantics interface, inadequate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
