We introduce an extension to CCG that allows form and function to be represented simultaneously, reducing the proliferation of modifier categories seen in standard CCG analyses. W...
We propose a novel unsupervised approach for distinguishing literal and non-literal use of idiomatic expressions. Our model combines an unsupervised and a supervised classifier. T...
We describe a process for automatically detecting decision-making sub-dialogues in multi-party, human-human meetings in real-time. Our basic approach to decision detection involve...
Matthew Frampton, Jia Huang, Trung H. Bui, Stanley...
This paper presents an investigation of the relation between words and their gender in two gendered languages: German and Romanian. Gender is an issue that has long preoccupied li...
We present a system that finds short definitions of terms on Web pages. It employs a Maximum Entropy classifier, but it is trained on automatically generated examples; hence, it i...