文献类型：期刊文献

英文题名：Enhancing Chinese abbreviation prediction with LLM generation and contrastive evaluation

作者：Liu, Jingping[1];Tian, Xianyang[1];Tong, Hanwen[2];Xie, Chenhao[2];Ruan, Tong[1];Cong, Lin[3];Wu, Baohua[3];Wang, Haofen[4]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Fudan Univ, Sch Comp Sci, Shanghai 200438, Peoples R China;[3]Alibaba Grp, Hangzhou 311100, Peoples R China;[4]Tongji Univ, Coll Design & Innovat, Shanghai 200092, Peoples R China

年份：2024

卷号：61

期号：4

外文期刊名：INFORMATION PROCESSING & MANAGEMENT

收录：;EI(收录号：20241916066935);WOS:【SSCI(收录号:WOS:001240775100001)，SCI-EXPANDED(收录号:WOS:001240775100001)】；

基金：This paper is supported by the National Natural Science Foundation of China (No. 62306112) , Shanghai Sailing Program (No. 23YF1409400) , Shanghai Pilot Program for Basic Research (No. 22TQ1400100-20) , and Alibaba Group through Alibaba Innovative Research Program.

语种：英文

外文关键词：Chinese abbreviation prediction; LLM generation; Contrastive evaluation

摘要：Chinese abbreviation prediction plays an important role in natural language processing. The prevalent approach often utilizes generation models to predict abbreviations for full forms, but relying solely on a single generation model may not yield high -quality abbreviations. We emphasize the importance of introducing an evaluation model after the generation model to assess the rationality of generated abbreviations. Hence, in this paper, we propose a novel two -stage method with LLM generation and contrastive evaluation for Chinese abbreviation prediction. In the first stage, we design a type discriminator to determine the abbreviation type and then introduce a pre -trained and fine-tuned LLM to generate multiple candidate abbreviations. In the second stage, we propose a contrastive evaluation model to assess the rationality of the candidates based on the abbreviation scorer and phrase scorer with a joint learning strategy. Experiments on two public datasets indicate that our method outperforms the current state-of-the-art method, achieving improvements of 3.32% and 1.73%, respectively. More importantly, we deploy it on the Fliggy application and the 20 -day online A/B testing shows a 0.65% increase in Point of Interest Recognition Rate and a 1.37% increase in Page View Click -Through Rate when using abbreviations predicted by our method in the search system.