It has been widely observed that different NLP applications require different sense granularities in order to best exploit word sense distinctions, and that for many applications ...
Rion Snow, Sushant Prakash, Daniel Jurafsky, Andre...
Grounded language models represent the relationship between words and the non-linguistic context in which they are said. This paper describes how they are learned from large corpo...
Assessing semantic similarity between text documents is a crucial aspect in Information Retrieval systems. In this work, we propose to use hyperlink information to derive a simila...
In this paper, we describe a reversibleletter-to-sound/soundto-letter generation system based on an approach which combines a rule-based formalism with data-driven techniques. We ...
The MT system described in this paper combines hand-built analysis and generation components with automatically learned example-based transfer patterns. Up to now, the transfer co...