Fusion of discourse structural position encoding for neural machine translation
Most of existing document-level neural machine translation (DocNMT) methods focus on exploring the utilization of the lexical information of context,which ignore the structural relationships among the cross-sentence discourse semantic units.Therefore,multiple discourse structural position encoding s...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2020-06-01
|
| Series: | 智能科学与技术学报 |
| Subjects: | |
| Online Access: | http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202016 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846171148996313088 |
|---|---|
| author | Xiaomian KANG Chengqing ZONG |
| author_facet | Xiaomian KANG Chengqing ZONG |
| author_sort | Xiaomian KANG |
| collection | DOAJ |
| description | Most of existing document-level neural machine translation (DocNMT) methods focus on exploring the utilization of the lexical information of context,which ignore the structural relationships among the cross-sentence discourse semantic units.Therefore,multiple discourse structural position encoding strategies were proposed to represent the positional relationships among the words in discourse units over the discourse tree based on rhetorical structure theory (RST).Experimental results show that the source-side discourse structural position information is effectively fused into the DocNMT models underlying the Transformer architecture by the position encoding,and the translation quality is improved significantly. |
| format | Article |
| id | doaj-art-d66f0f0d436b4901a4f2f450d85b977b |
| institution | Kabale University |
| issn | 2096-6652 |
| language | zho |
| publishDate | 2020-06-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 智能科学与技术学报 |
| spelling | doaj-art-d66f0f0d436b4901a4f2f450d85b977b2024-11-11T06:51:54ZzhoPOSTS&TELECOM PRESS Co., LTD智能科学与技术学报2096-66522020-06-01214415259637757Fusion of discourse structural position encoding for neural machine translationXiaomian KANGChengqing ZONGMost of existing document-level neural machine translation (DocNMT) methods focus on exploring the utilization of the lexical information of context,which ignore the structural relationships among the cross-sentence discourse semantic units.Therefore,multiple discourse structural position encoding strategies were proposed to represent the positional relationships among the words in discourse units over the discourse tree based on rhetorical structure theory (RST).Experimental results show that the source-side discourse structural position information is effectively fused into the DocNMT models underlying the Transformer architecture by the position encoding,and the translation quality is improved significantly.http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202016neural machine translation;discourse structure;position encoding;discourse analysis;rhetorical structure theory |
| spellingShingle | Xiaomian KANG Chengqing ZONG Fusion of discourse structural position encoding for neural machine translation 智能科学与技术学报 neural machine translation;discourse structure;position encoding;discourse analysis;rhetorical structure theory |
| title | Fusion of discourse structural position encoding for neural machine translation |
| title_full | Fusion of discourse structural position encoding for neural machine translation |
| title_fullStr | Fusion of discourse structural position encoding for neural machine translation |
| title_full_unstemmed | Fusion of discourse structural position encoding for neural machine translation |
| title_short | Fusion of discourse structural position encoding for neural machine translation |
| title_sort | fusion of discourse structural position encoding for neural machine translation |
| topic | neural machine translation;discourse structure;position encoding;discourse analysis;rhetorical structure theory |
| url | http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202016 |
| work_keys_str_mv | AT xiaomiankang fusionofdiscoursestructuralpositionencodingforneuralmachinetranslation AT chengqingzong fusionofdiscoursestructuralpositionencodingforneuralmachinetranslation |