ACL
2006
13 years 11 months ago
2006
This paper proposes a method for incrementally translating English spoken language into Japanese. To realize simultaneous translation between languages with different word order, ...
ACL
2006
13 years 11 months ago
2006
We introduce a new multi-threaded parsing algorithm on unification grammars designed specifically for multimodal interaction and noisy environments. By lifting some traditional co...
ACL
2006
13 years 11 months ago
2006
We report on the development of a new automatic feedback model to improve information retrieval in digital libraries. Our hypothesis is that some particular sentences, selected ba...
ACL
2006
13 years 11 months ago
2006
Speech recognition problems are a reality in current spoken dialogue systems. In order to better understand these phenomena, we study dependencies between speech recognition probl...
ACL
2006
13 years 11 months ago
2006
Most information extraction systems either use hand written extraction patterns or use a machine learning algorithm that is trained on a manually annotated corpus. Both of these a...
ACL
2006
13 years 11 months ago
2006
We present a method for unsupervised topic modelling which adapts methods used in document classification (Blei et al., 2003; Griffiths and Steyvers, 2004) to unsegmented multi-pa...
ACL
2006
13 years 11 months ago
2006
This paper demonstrates a conceptually simple but effective method of increasing the accuracy of QA systems on factoid-style questions. We define the notion of an inverted questio...
ACL
2006
13 years 11 months ago
2006
In this paper, we discuss how to utilize the co-occurrence of answers in building an automatic question answering system that answers a series of questions on a specific topic in ...
ACL
2006
13 years 11 months ago
2006
This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarizatio...
ACL
2006
13 years 11 months ago
2006
We present an automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank. Starting...