This paper describes the application of the PARADISE evaluation framework to the corpus of 662 human-computer dialogues collected in the June 2000 Darpa Communicator data collecti...
Marilyn A. Walker, Rebecca J. Passonneau, Julie E....
Multimodal dialogue systems allow users to input information in multiple modalities. These systems can handle simultaneous or sequential composite multimodal input. Different coor...
We propose a statistical method that finds the maximum-probability segmentation of a given text. This method does not require training data because it estimates probabilities from...
In statistical machine translation, the generation of a translation hypothesis is computationally expensive. If arbitrary wordreorderings are permitted, the search problem is NP-h...
One of the central issues for information extraction (IE) systems is the cost of customization from one scenario to another. Research on the automated acquisition of patterns is i...
This paper presents a method for unsupervised discovery of semantic patterns. Semantic patterns are useful for a variety of text understanding tasks, in particular for locating ev...
In this paper we propose a competition learning approach to coreference resolution. Traditionally, supervised machine learning approaches adopt the singlecandidate model. Neverthe...
Xiaofeng Yang, Guodong Zhou, Jian Su, Chew Lim Tan
The standard pipeline approach to semantic processing, in which sentences are morphologically and syntactically resolved to a single tree before they are interpreted, is a poor fi...
Standard IR systems can process queries such as “web NOT internet”, enabling users who are interested in arachnids to avoid documents about computing. The documents retrieved ...
In a headed tree, each terminal word can be uniquely labeled with a governing word and grammatical relation. This labeling is a summary of a syntactic analysis which eliminates de...