| アイテムタイプ |
会議発表論文 / Conference Paper(1) |
| 公開日 |
2025-07-16 |
| タイトル |
|
|
タイトル |
Generating Diverse Translation with Perturbed kNN-MT |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ |
conference paper |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Nishida, Yuto
Morishita, Makoto
上垣外, 英剛
渡辺, 太郎
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Generating multiple translation candidates would enable users to choose the one that satisfies their needs.Although there has been work on diversified generation, there exists room for improving the diversity mainly because the previous methods do not address the overcorrection problem$2014the model underestimates a prediction that is largely different from the training data, even if that prediction is likely.This paper proposes methods that generate more diverse translations by introducing perturbed k-nearest neighbor machine translation (kNN-MT).Our methods expand the search space of kNN-MT and help incorporate diverse words into candidates by addressing the overcorrection problem.Our experiments show that the proposed methods drastically improve candidate diversity and control the degree of diversity by tuning the perturbation’s magnitude. |
| 書誌情報 |
en : Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
p. 9-31,
ページ数 23,
発行日 2024-03
|
| 会議情報 |
|
|
|
会議名 |
The 18th Conference of the European Chapter of the Association for Computational Linguistics |
|
|
開始年 |
2024 |
|
|
開始月 |
03 |
|
|
開始日 |
21 |
|
|
終了年 |
2024 |
|
|
終了月 |
03 |
|
|
終了日 |
22 |
|
|
開催期間 |
2024-03-21 - 2024-03-22 |
|
|
開催地 |
St. Julian’s, Malta |
|
開催国 |
MLT |
| 出版者 |
|
|
出版者 |
Association for Computational Linguistics |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://aclanthology.org/2024.eacl-srw.2/ |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
$00A9 2024 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. |
| 著者版フラグ |
|
|
出版タイプ |
NA |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP21H05054 |
|
|
研究課題名 |
多元自動通訳システムと評価法に関する研究とその応用展開 |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP21K17801 |
|
|
研究課題名 |
共参照クラスタを明示的に推定する先行詞の解析誤りに対し頑健な共参照解析手法 |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP23H03458 |
|
|
研究課題名 |
漸進的な知識の拡張を行う汎用自然言語生成モデルの研究 |