U.S. Department of Energy

Pacific Northwest National Laboratory

A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language

Publish Date: 
Wednesday, June 3, 2015
Semantic roles play a significant role in extracting knowledge from text. The current unsupervised approaches utilize features from grammar structures, to induce semantic roles on to the words. The dependence on these grammars makes it difficult to adapt to noisy and new languages. In this paper we develop a data-driven approach for identifying semantic roles, where we are truly unsupervised till the point where we need to learn few rules for identifying the place where semantic role occurs. Specifically we develop a modified- ADIOS algorithm based on ADIOS (Solan, 2006) to learn grammar structures, and use grammar structures to learn the rules for identifying the semantic roles based on the context in which the grammar structures appeared. We improved the scalability of the approach by generalizing the words in the language to clusters of words.
Datla VV, D Lin, M Louwerse, and A Vishnu. 2015. "A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language." In Empirical Methods in Natural language processing. PNNL-SA-110835, Pacific Northwest National Laboratory, Richland, WA.
| Pacific Northwest National Laboratory