We investigate the automatic construction of visual scenes via a hybrid evolutionary/hill-climbing approach using a correlationbased fitness function. This forms part of The Painti...
In this work, we develop and evaluate a wide range of feature spaces for deriving Levinstyle verb classifications (Levin, 1993). We perform the classification experiments using Ba...
This paper presents the application of WordNet-based semantic relatedness measures to Automatic Speech Recognition (ASR) in multi-party meetings. Different word-utterance context ...
Identification of transliterated names is a particularly difficult task of Named Entity Recognition (NER), especially in the Chinese context. Of all possible variations of trans...
We use an EM algorithm to learn user models in a spoken dialog system. Our method requires automatically transcribed (with ASR) dialog corpora, plus a model of transcription error...