Exploring automatic theme identification: a rule-based approach

Abstract

Abstract. Knowledge about Theme-Rheme serves the interpretation of a text in terms of its thematic progression and provides a window into the topicality of a text as well as text type (genre). This is potentially relevant for NLP tasks such as information extraction and text classification. To explore this potential, large corpora annotated for Theme-Rheme organization are needed. We report on a rule-based system for the automatic identification of Theme to be employed for corpus annotation. The rules are manually derived from a set of sentences parsed syntactically with the Stanford parser and analyzed in terms of Theme on the basis of Systemic Functional Grammar (SFG). We describe the development of the rule set and the automatic procedure of Theme identification and assess the validity of the approach by application to some authentic text data.

Computational Methods for Corpus Annotation and Analysis

“…Most tools that are currently available, however, are for sentence generation using computational grammars in the SFL formalism, such as the KPML development environment (Bateman 1997), or for assisting manual lexico-grammatical text analysis within the SFL framework, such as Systemics (O'Halloran and Judd 2002). Schwarz et al (2008) designed a rule-based system for automatically identifying simple Themes (i.e., Themes consisting of one ideational element only). For example, Kappagoda (2009) discussed the rationale for using SFL in automated text mining, developed a grammatical annotation scheme to enrich text corpora, and trained a machine learner for automatic annotation of word functions in the group.…”