Automatic generation of text summaries for spoken language faces the problem of containing incorrect words and passages due to speech recognition errors. This paper describes comp...
Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser ar...
A major obstacle to the construction of a probabilistic translation model is the lack of large parallel corpora. In this paper we first describe a parallel text mining system that...
A long-standing issue regarding algorithms that manipulate context-free grammars (CFGs) in a "top-down" leftto-right fashion is that left recursion can lead to nontermin...
This paper proposes a way to improve the translation quality by using information on dialogue participants that is easily obtained from outside the translation component. We incor...