We describe two probabilistic models for unsupervised word-sense disambiguation using parallel corpora. The first model, which we call the Sense model, builds on the work of Diab ...
The parameters of statistical translation models are typically estimated from sentence-aligned parallel corpora. We show that significant improvements in the alignment and transla...
Discovering the significant relations embedded in documents would be very useful not only for information retrieval but also for question answering and summarization. Prior method...
In this paper, we describe a new methodology to develop mixed-initiative spoken dialog systems, which is based on the extensive use of simulations to accelerate the development pr...
Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method f...