MBT2: a method for combining fragments of examples in example-based translation
Artificial Intelligence - Special issue: AI research in Japan
Learning Translation Templates from Bilingual Translation Examples
Applied Intelligence
Stochastic inversion transduction grammars and bilingual parsing of parallel corpora
Computational Linguistics
Modeling with structures in statistical machine translation
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Finding structural correspondences from bilingual parsed corpus for corpus-based translation
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
| Hi-index | 0.00 |
In this paper, we propose a new approach for acquiring translation templates automatically from unannotated bilingual spoken language corpora. Two basic algorithms are adopted: a grammar induction algorithm, and an alignment algorithm using Bracketing Transduction Grammar. The approach is unsupervised, statistical, data-driven, and employs no parsing procedure. The acquisition procedure consists of two steps. First, semantic groups and phrase structure groups are extracted from both the source language and the target language through a boosting procedure, in which a synonym dictionary is used to generate the seed groups of the semantic groups. Second, an alignment algorithm based on Bracketing Transduction Grammar aligns the phrase structure groups. The aligned phrase structure groups are post-processed, yielding translation templates. Preliminary experimental results show that the algorithm is effective.