EMNLP
2009
13 years 2 months ago
2009
Randomised techniques allow very big language models to be represented succinctly. However, being batch-based they are unsuitable for modelling an unbounded stream of language whi...
ACL
1990
13 years 5 months ago
1990
This paper describes a new hardware algorithm for morpheme extraction and its implementation on a specific machine (MEX-I), as the first step toward achieving natural language par...
RIDE
1998
IEEE
13 years 8 months ago
1998
IEEE
This paper presents a method of automatically creating hypermedia documents from conventional transcriptions of television programs. Using parallel text alignment techniques, the ...
SIGIR
2003
ACM
13 years 9 months ago
2003
ACM
This paper presents a novel domain-independent text segmentation method, which identifies the boundaries of topic changes in long text documents and/or text streams. The method c...
MMM
2010
Springer
14 years 1 months ago
2010
Springer
In this paper, we introduce and evaluate two novel approaches, one using video stream and the other using close-caption text stream, for segmenting TV news into stories. The segmen...