We observe that (1) how a given named entity (NE) is translated (i.e., either semantically or phonetically) depends greatly on its associated entity type, and (2) entities within ...
The computation of selectional preferences, the admissible argument values for a relation, is a well-known NLP task with broad applicability. We present LDA-SP, which utilizes Lin...
To date, few attempts have been made to develop and validate methods for automatic evaluation of linguistic quality in text summarization. We present the first systematic assessme...
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
Open-ended spoken interactions are typically characterised by both structural complexity and high levels of uncertainty, making dialogue management in such settings a particularly...