Tracker Text Segmentation Approach: Integrating Complex Lexical and Conversation Cue Features

Abstract

While text segmentation is a topic which has received a great attention since 9/11, most of current research projects remain focused on expository texts, stories and broadcast news. Current segmentation methods are well suited for written and structured texts making use of their distinctive macro-level structures. Text segmentation of transcribed multi-party conversation presents a different challenge given the lack of linguistic features such as headings, paragraph, and well formed sentences. This paper describes an algorithm suited for transcribed meeting conversations combining semantically complex lexical relations with conversational cue phrases to build lexical chains in determining topic boundaries.