TCohPrompt: task-coherent prompt-oriented fine-tuning for relation extraction

Uloženo v:
Podrobná bibliografie
Vydáno v:Complex & Intelligent Systems vol. 10, no. 6 (Dec 2024), p. 7565
Hlavní autor: Long, Jun
Další autoři: Yin, Zhuoying, Liu, Chao, Huang, Wenti
Vydáno:
Springer Nature B.V.
Témata:
On-line přístup:Citation/Abstract
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

MARC

LEADER 00000nab a2200000uu 4500
001 3117209474
003 UK-CbPIL
022 |a 2199-4536 
022 |a 2198-6053 
024 7 |a 10.1007/s40747-024-01563-4  |2 doi 
035 |a 3117209474 
045 2 |b d20241201  |b d20241231 
100 1 |a Long, Jun  |u Central South University, School of Computer Science and Engineering, Changsha, China (GRID:grid.216417.7) (ISNI:0000 0001 0379 7164) 
245 1 |a TCohPrompt: task-coherent prompt-oriented fine-tuning for relation extraction 
260 |b Springer Nature B.V.  |c Dec 2024 
513 |a Journal Article 
520 3 |a Prompt-tuning has emerged as a promising approach for improving the performance of classification tasks by converting them into masked language modeling problems through the insertion of text templates. Despite its considerable success, applying this approach to relation extraction is challenging. Predicting the relation, often expressed as a specific word or phrase between two entities, usually requires creating mappings from these terms to an existing lexicon and introducing extra learnable parameters. This can lead to a decrease in coherence between the pre-training task and fine-tuning. To address this issue, we propose a novel method for prompt-tuning in relation extraction, aiming to enhance the coherence between fine-tuning and pre-training tasks. Specifically, we avoid the need for a suitable relation word by converting the relation into relational semantic keywords, which are representative phrases that encapsulate the essence of the relation. Moreover, we employ a composite loss function that optimizes the model at both token and relation levels. Our approach incorporates the masked language modeling (MLM) loss and the entity pair constraint loss for predicted tokens. For relation level optimization, we use both the cross-entropy loss and TransE. Extensive experimental results on four datasets demonstrate that our method significantly improves performance in relation extraction tasks. The results show an average improvement of approximately 1.6 points in F1 metrics compared to the current state-of-the-art model. Codes are released at <ext-link xlink:href="https://github.com/12138yx/TCohPrompt" ext-link-type="url">https://github.com/12138yx/TCohPrompt</ext-link>. 
653 |a Performance enhancement 
653 |a Performance prediction 
653 |a Words (language) 
653 |a Coherence 
653 |a Language 
653 |a Text categorization 
653 |a Computer science 
653 |a Intelligent systems 
653 |a Classification 
653 |a Natural language processing 
653 |a Keywords 
653 |a Entropy 
653 |a Semantics 
700 1 |a Yin, Zhuoying  |u Central South University, School of Computer Science and Engineering, Changsha, China (GRID:grid.216417.7) (ISNI:0000 0001 0379 7164) 
700 1 |a Liu, Chao  |u Guizhou Rural Credit Union, Guiyang, China (GRID:grid.216417.7) 
700 1 |a Huang, Wenti  |u Hunan University of Science and Technology, School of Computer Science and Engineering, Xiangtan, China (GRID:grid.411429.b) (ISNI:0000 0004 1760 6172) 
773 0 |t Complex & Intelligent Systems  |g vol. 10, no. 6 (Dec 2024), p. 7565 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3117209474/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3117209474/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch