This paper proposes a Japanese/English crosslanguage information retrieval (CLIR) system targeting technical documents. Our system first translates a given query containing techni...
The University of Maryland participated in the English and Czech tasks. For English, one monolingual run using only fields based on fully automatic transcription (the required con...
We present an algorithm for bilingual word alignment that extends previous work by treating multi-word candidates on a par with single words, and combining some simple assumptions...
The non-English Web is growing at breakneck speed, but available language processing tools are mostly English based. Taxonomies are a case in point: while there are plenty of comm...
Xuerui Wang, Andrei Z. Broder, Evgeniy Gabrilovich...
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...