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

TL;DR

This paper presents an unsupervised, data-driven method for semantic role labeling that leverages induced grammar structures, improving adaptability to noisy and new languages while achieving results comparable to supervised models.

Contribution

Develops a modified-ADIOS algorithm to learn grammar structures and rules for semantic roles without relying on annotated data, enhancing flexibility and applicability.

Findings

Results are comparable with state-of-the-art supervised models

Method is fully unsupervised up to rule learning

Approach improves adaptability to noisy and new languages

Abstract

Semantic roles play an important role in extracting knowledge from text. Current unsupervised approaches utilize features from grammar structures, to induce semantic roles. The dependence on these grammars, however, makes it difficult to adapt to noisy and new languages. In this paper we develop a data-driven approach to identifying semantic roles, the approach is entirely unsupervised up to the point where rules need to be learned to identify the position the semantic role occurs. Specifically we develop a modified-ADIOS algorithm based on ADIOS Solan et al. (2005) to learn grammar structures, and use these grammar structures to learn the rules for identifying the semantic roles based on the context in which the grammar structures appeared. The results obtained are comparable with the current state-of-art models that are inherently dependent on human annotated data.