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...
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
This paper examines the phenomenon of consonant spreading in Arabic stems. Each spreading involves a local surface copying of an underlying consonant, and, in certain phonological...
Word graphs are able to represent a large number of different utterance hypotheses in a very compact manner. However, usually they contain a huge amount of redundancy in terms of ...
Cross-document coreference occurs when the same person, place, event, or concept is discussed in more than one text source. Computer recognition of this phenomenon is important be...