Type

Conference Proceedings

Authors

Andy Way
Gareth J. F. Jones
Johannes Leveling
Jie Jiang
Jinming Min

Subjects

Computer Science

Topics
machine translating named entity translation okapi model training data query expansion retrieval models cross language information retrieval statistical machine translation

DCU's experiments in NTCIR-8 IR4QA task (2010)

Abstract We describe DCU's participation in the NTCIR-8 IR4QA task [16]. This task is a cross-language information retrieval(CLIR) task from English to Simplified Chinese which seeks to provide relevant documents for later cross language question answering (CLQA) tasks. For the IR4QA task, we submitted 5 official runs including two monolingual runs and three CLIR runs. For the monolingual retrieval we tested two information retrieval models. The results show that the KL-Divergence language model method performs better than the Okapi BM25 model for the Simplified Chinese retrieval task. This agrees with our previous CLIR experimental results at NTCIR-5. For the CLIR task, we compare query translation and document translation methods. In the query translation based runs, we tested a method for query expansion from external resource (QEE) before query translation. Our result for this run is slightly lower than the run without QEE. Our results show that the document translation method achieves 68.24% MAP performance compared to our best query translation run. For the document translation method, we found that the main issue is the lack of named entity translation in the documents since we do not have a suitable parallel corpus for training data for the statistical machine translation system. Our best CLIR run comes from the combination of query translation using Google translate and the KL-Divergence language model retrieval method. It achieves 79.94% MAP relative to our best monolingual run.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> Subject = Computer Science
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: Centre for Next Generation Localisation (CNGL)
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> Subject = Computer Science: Machine translating
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres

Full list of authors on original publication

Andy Way, Gareth J. F. Jones, Johannes Leveling, Jie Jiang, Jinming Min

Experts in our system

1
Andy Way
Dublin City University
Total Publications: 229
 
2
Gareth J. F. Jones
Dublin City University
Total Publications: 297
 
3
Johannes Leveling
Dublin City University
Total Publications: 66
 
4
Jinming Min
Dublin City University
Total Publications: 10