We present a language-independent and unsupervised algorithm for the segmentation of words into morphs. The algorithm is based on a new generative probabilistic model, which makes...
This paper investigates the correlation between acoustic confidence scores as returned by speech recognizers with recognition quality. We report the results of two machine learni...
Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic ...
In this paper, we elucidate how Korean temporal markers, OE and DONGAN contribute to specifying the event time and formalize it in terms of typed lambda calculus. We also present ...
The model used by the CCG parser of Hockenmaier and Steedman (2002b) would fail to capture the correct bilexical dependencies in a language with freer word order, such as Dutch. T...