Exploiting headword dependency and predictive clustering for language modeling (2002)
Cached
Download Links
| Venue: | In EMNLP |
| Citations: | 7 - 5 self |
BibTeX
@INPROCEEDINGS{Gao02exploitingheadword,
author = {Jianfeng Gao},
title = {Exploiting headword dependency and predictive clustering for language modeling},
booktitle = {In EMNLP},
year = {2002},
pages = {248--256}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper presents several practical ways of incorporating linguistic structure into language models. A headword detector is first applied to detect the headword of each phrase in a sentence. A permuted headword trigram model (PHTM) is then generated from the annotated corpus. Finally, PHTM is extended to a cluster PHTM (C-PHTM) by defining clusters for similar words in the corpus. We evaluated the proposed models on the realistic application of Japanese Kana-Kanji conversion. Experiments show that C-PHTM achieves 15 % error rate reduction over the word trigram model. This
