Resource limitation is challenging for crossdomain adaption. This paper employs patterns identified from a monolingual in-domain corpus and patterns learned from the post-edited translation results, and translation model as well as language model learned from pseudo bilingual corpora produced by a baseline MT system. The adaptation from a government document domain to a medical record domain sh...

In this paper, we present a set of experiments towards a cross-language Greek-English Question-Answering (QA) system. After exploring previous work done both in monolingual and cross-lingual QA, we have applied the common “question reformulation” strategy used in monolingual systems along with different translation strategies and evaluated the results with the TREC question set. We have mainly ...

This paper describes AliQAn, a monolingual open-domain Question Answering (QA) System developed in the Department of Language Processing and Information Systems at the University of Alicante for CLEF-2005 Spanish monolingual QA evaluation task. Our approach is based fundamentally on the use of syntactic pattern recognition in order to identify possible answers. Beside, Word Sense Disambiguation...

Abstract. This paper describes the participation of RICOH in the monolingual and cross-lingual information retrieval tasks on German Indexing and Retrieval Testdatabase (GIRT) in the Cross-Language Evaluation Forum (CLEF) 2004. We used a morphological analyzer for word decompounding and parallel corpora for cross-lingual information retrieval. The performance of cross-lingual information retrie...

Most models of word production converge on the assumption that selecting a specific to name is competitive process. Monolingual speakers experience lexical competition in their spoken language (i.e., within-language competition), but bilingual who constantly juggle two sets items face within- and between-language competition. It has been argued one reasons perform poorly linguistic tasks compar...