Japanese dependency structure analysis based on maximum entropy models
EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Three generative, lexicalised models for statistical parsing
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Using decision trees to construct a practical parser
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Statistical decision-tree models for parsing
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Japanese dependency structure analysis based on support vector machines
EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
Linear-time dependency analysis for Japanese
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Sequential dependency analysis for online spontaneous speech processing
Speech Communication
Computational Linguistics
A unified single scan algorithm for Japanese base phrase chunking and dependency parsing
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Using a partially annotated corpus to build a dependency parser for japanese
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
Hi-index | 0.00 |
Backward beam search for dependency analysis of Japanese is proposed. As dependencies normally go from left to right in Japanese, it is effective to analyze sentences backwards (from right to left). The analysis is based on a statistical method and employs a beam search strategy. Based on experiments varying the beam search width, we found that the accuracy is not sensitive to the beam width and even the analysis with a beam width of 1 gets almost the same dependency accuracy as the best accuracy using a wider beam width. This suggested a deterministic algorithm for backwards Japanese dependency analysis, although still the beam search is effective as the N-best sentence accuracy is quite high. The time of analysis is observed to be quadratic in the sentence length.