We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
In this paper, an automatic method for Persian WordNet construction based on Prenceton WordNet 2.1 (PWN) is introduced. The proposed approach uses Persian and English corpora as w...
We present new direct data analysis showing that dynamically-built context-dependent phrasal translation lexicons are more useful resources for phrase-based statistical machine tr...
Recent work on the transfer of semantic information across languages has been recently applied to the development of resources annotated with Frame information for different non-En...
Roberto Basili, Diego De Cao, Danilo Croce, Bonave...
In TREC-9, we participated in the English-Chinese Cross Language, 10GB Web data ad-hoc retrieval as well as the Question-Answering tracks, all using automatic procedures. All thes...
Kui-Lam Kwok, Laszlo Grunfeld, Norbert Dinstl, M. ...