In this paper we describe a novel approach to lexical chain based segmentation of broadcast news stories. Our segmentation system SeLeCT is evaluated with respect to two other lexical cohesion based segmenters TextTiling and C99. Using the Pk and WindowDiff evaluation metrics we show that SeLeCT outperforms both systems on spoken news transcripts (CNN) while the C99 algorithm performs best on t...

We are compiling a corpus of Dutch texts annotated with discourse structure and lexical cohesion, containing initially 80 texts from expository and persuasive genres. We are using this resource for corpus-based studies of discourse relations, discourse markers, cohesion, and genre differences. We are also exploring the possibilities of automatic text segmentation and semi-automatic discourse an...

This paper proposes to integrate multi-modal features using conditional random fields (CRF) for broadcast news story segmentation. We study story boundary cues from lexical, audio and video modalities, where lexical features consist of lexical similarity, chain strength and overall cohesiveness, acoustic features involve pause duration, pitch, speaker change and audio event type, and visual fea...

This paper is motivated by the observation that not all adjectives in Chinese have a canonical antonym. For example, most Chinese speakers choose to translate the English word dishonest into a word string bu chengshi ‘not honest’ instead of any antonym candidates of chengshi suggested in antonym dictionaries. Our discourse evidence from corpus data suggests that bu chengshi is evolving into a w...

Lexical acquisition is a critical stage of language development, during which human infants learn a set of word forms and their association with meanings, starting from little a priori knowledge about words they do not even know whether there are words in their mother tongues. How do the infants infer individual words from the continuous speech stream to which they are exposed? This paper inten...

The study of lexical semantics has produced a systematic analysis of relationships between content words that has greatly bene ted both lexical search tools and natural language processing systems. We describe research toward a common algorithmic core for these two applications. We rst introduce a database system called FreeNet that facilitates the description and exploration nite binary relati...

This PhD thesis focuses on the problems encountered when developing automatic speech recognition for under-resourced languages with a writing system without explicit separation between words. The specificity of the languages covered in our work requires automatic segmentation of text corpus into words in order to make the n-gram language modeling applicable. While the lack of text data has an i...