WEKO3
アイテム
Hierarchical Statistical Machine Translation Using Sampling Based Alignment
https://ipsj.ixsq.nii.ac.jp/records/98182
https://ipsj.ixsq.nii.ac.jp/records/98182d3cc7429-9341-4c1e-8fa4-bc023911b59f
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
|
|
Copyright (c) 2014 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | SIG Technical Reports(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2014-01-30 | |||||||
| タイトル | ||||||||
| タイトル | Hierarchical Statistical Machine Translation Using Sampling Based Alignment | |||||||
| タイトル | ||||||||
| 言語 | en | |||||||
| タイトル | Hierarchical Statistical Machine Translation Using Sampling Based Alignment | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | 言語モデル・統計処理 | |||||||
| 資源タイプ | ||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||
| 資源タイプ | technical report | |||||||
| 著者所属 | ||||||||
| IPS, Waseda University | ||||||||
| 著者所属 | ||||||||
| IPS, Waseda University | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| IPS, Waseda University | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| IPS, Waseda University | ||||||||
| 著者名 |
Tongxu, Liu
Yves, Lepage
× Tongxu, Liu Yves, Lepage
|
|||||||
| 著者名(英) |
Tongxu, Liu
Yves, Lepage
× Tongxu, Liu Yves, Lepage
|
|||||||
| 論文抄録 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | We propose an extension of the sampling-based alignment technique to implement the hierarchical phrases-based model. The proposed technique outputs a hierarchical phrase based rule table. It is learned from a bi-text without any syntactic information or any linguistic commitment. We expect the following advantages from our rule tables: 1. better reordering, 2. better translation of discontinuous phrases. | |||||||
| 論文抄録(英) | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | We propose an extension of the sampling-based alignment technique to implement the hierarchical phrases-based model. The proposed technique outputs a hierarchical phrase based rule table. It is learned from a bi-text without any syntactic information or any linguistic commitment. We expect the following advantages from our rule tables: 1. better reordering, 2. better translation of discontinuous phrases. | |||||||
| 書誌レコードID | ||||||||
| 収録物識別子タイプ | NCID | |||||||
| 収録物識別子 | AN10115061 | |||||||
| 書誌情報 |
研究報告自然言語処理(NL) 巻 2014-NL-215, 号 1, p. 1-5, 発行日 2014-01-30 |
|||||||
| Notice | ||||||||
| SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||
| 出版者 | ||||||||
| 言語 | ja | |||||||
| 出版者 | 情報処理学会 | |||||||