|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM32137312X |
| 003 |
DE-627 |
| 005 |
20231225175653.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2021.3058341
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1071.xml
|
| 035 |
|
|
|a (DE-627)NLM32137312X
|
| 035 |
|
|
|a (NLM)33577448
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Zuchao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Text Compression-Aided Transformer Encoding
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 07.06.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant improvements in the performance of many NLP tasks. Though the Transformer encoder may effectively capture general information in its resulting representations, the backbone information, meaning the gist of the input text, is not specifically focused on. In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily. Our explicit text compression approaches use dedicated models to compress text, while our implicit text compression approach simply adds an additional module to the main model to handle text compression. We propose three ways of integration, namely backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the backbone information into Transformer-based models for various downstream tasks. Our evaluation on benchmark datasets shows that the proposed explicit and implicit text compression approaches improve results in comparison to strong baselines. We therefore conclude, when comparing the encodings to the baseline models, text compression helps the encoders to learn better language representations
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Zhuosheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhao, Hai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Rui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chen, Kehai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Utiyama, Masao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sumita, Eiichiro
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 44(2022), 7 vom: 12. Juli, Seite 3840-3857
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:44
|g year:2022
|g number:7
|g day:12
|g month:07
|g pages:3840-3857
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2021.3058341
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 44
|j 2022
|e 7
|b 12
|c 07
|h 3840-3857
|