A corpus balancing method for language model construction
CICLing'03 Proceedings of the 4th international conference on Computational linguistics and intelligent text processing
Defining classifier regions for WSD ensembles using word space features
MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Overview of the CLEF 2005 multilingual question answering track
CLEF'05 Proceedings of the 6th international conference on Cross-Language Evalution Forum: accessing Multilingual Information Repositories
Cross-language french-english question answering using the DLT system at CLEF 2005
CLEF'05 Proceedings of the 6th international conference on Cross-Language Evalution Forum: accessing Multilingual Information Repositories
Architecture and evaluation of BRUJA, a multilingual question answering system
Information Retrieval
| Hi-index | 0.00 |
One major problem of state-of-the-art Cross Language Question Answering systems is the translation of user questions. This paper proposes combining the potential of multiple translation machines in order to improve the final answering precision. In particular, it presents three different methods for this purpose. The first one focuses on selecting the most fluent translation from a given set; the second one combines the passages recovered by several question translations; finally, the third one constructs a new question reformulation by merging word sequences from different translations. Experimental results demonstrated that the proposed approaches allow reducing the error rates in relation to a monolingual question answering exercise.