| Presentation | 2003/8/22 Sentence Matching Algorithm of Revised Documents with Considering Context Information Toshihiko MATSUNAGA, Mihoko KITAMURA, Toshiki MURATA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | By using documents that have versions of other languages, we are developing a translation system for revised documents. In this system, each original sentence before revised is matched with its original sentence after revised. When sentences are matched only based on their similarities, we cannot obtain correct results because their contexts are not considered. Therefore, we propose a way to divide documents into certain blocks, such as chapters and paragraphs, match the documents before revised with the ones after revised on a block basis as narrowing the scope of the documents and finally match each sentence before revised with the one after revised every block matched before. As a result of an experiment using this way, we confirmed that the matching accuracy between documents before revised and ones after revised has improved. In this paper, the summary of the translation system for revised documents using this way of matching will be shown. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | revised documents / sentence matching / text alignment / computer aided translation |
| Paper # | NLC2003-22 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2003/8/22(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Sentence Matching Algorithm of Revised Documents with Considering Context Information |
| Sub Title (in English) | |
| Keyword(1) | revised documents |
| Keyword(2) | sentence matching |
| Keyword(3) | text alignment |
| Keyword(4) | computer aided translation |
| 1st Author's Name | Toshihiko MATSUNAGA |
| 1st Author's Affiliation | Ubiquitous System Laboratory, Corporate RD Center, Oki Electric Industry Co., Ltd.() |
| 2nd Author's Name | Mihoko KITAMURA |
| 2nd Author's Affiliation | Ubiquitous System Laboratory, Corporate RD Center, Oki Electric Industry Co., Ltd. |
| 3rd Author's Name | Toshiki MURATA |
| 3rd Author's Affiliation | Ubiquitous System Laboratory, Corporate RD Center, Oki Electric Industry Co., Ltd. |
| Date | 2003/8/22 |
| Paper # | NLC2003-22 |
| Volume (vol) | vol.103 |
| Number (no) | 280 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |