| Item type |
SIG Technical Reports(1) |
| 公開日 |
2017-10-17 |
| タイトル |
|
|
タイトル |
Improving Neural Machine Translation with Linearized Dependency Tree Decoder |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Improving Neural Machine Translation with Linearized Dependency Tree Decoder |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
機械翻訳(2) |
| 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 |
|
|
|
Nara Institute of Science and Technology |
| 著者所属 |
|
|
|
Nara Institute of Science and Technology |
| 著者所属 |
|
|
|
Nara Institute of Science and Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Nara Institute of Science and Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Nara Institute of Science and Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Nara Institute of Science and Technology |
| 著者名 |
An, Nguyen Le
Ander, Martinez
Yuji, Matsumoto
|
| 著者名(英) |
An, Nguyen Le
Ander, Martinez
Yuji, Matsumoto
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In spite of achieving significant performance in recent years, there are some existing issues that Sequence-to-Sequence Neural Machine Translation still does not solve completely. Two of them are translation for long sentences and the over-translation. To address these two problems, we propose an approach that utilize more syntactic information, syntactic dependency information, so that the output is generated based on more abundant information. In addition, the outputs are presented not as a simple sequence of tokens but as a linear grammatical tree structure. In addition, the output of the model is presented not as a simple sequence of tokens but as a linearized tree construction. Experiments on the Europarl-v7 dataset of French-to-English translation demonstrate that our proposed method can produce dependency relations between words in the target language and improve BLEU scores by 1.57 and 2.40 on datasets consisting of sentences with up to 50 and 80 tokens, respectively. Furthermore, the proposed method also solved the ineffective translation for long sentences and repetition problems in Neural Machine Translation. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In spite of achieving significant performance in recent years, there are some existing issues that Sequence-to-Sequence Neural Machine Translation still does not solve completely. Two of them are translation for long sentences and the over-translation. To address these two problems, we propose an approach that utilize more syntactic information, syntactic dependency information, so that the output is generated based on more abundant information. In addition, the outputs are presented not as a simple sequence of tokens but as a linear grammatical tree structure. In addition, the output of the model is presented not as a simple sequence of tokens but as a linearized tree construction. Experiments on the Europarl-v7 dataset of French-to-English translation demonstrate that our proposed method can produce dependency relations between words in the target language and improve BLEU scores by 1.57 and 2.40 on datasets consisting of sentences with up to 50 and 80 tokens, respectively. Furthermore, the proposed method also solved the ineffective translation for long sentences and repetition problems in Neural Machine Translation. |
| 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 2017-NL-233,
号 10,
p. 1-7,
発行日 2017-10-17
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8779 |
| 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 |
IPSJ-NL17233010.pdf (873.3 kB)
