arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.00543cs.CL
收藏

用于定义生成的细粒度对比学习

Fine-grained Contrastive Learning for Definition Generation

Beijing University of Posts and Telecommunications(北京邮电大学);Tsinghua University(清华大学);University of California, San Diego(加州大学圣迭戈分校)

Hengyuan Zhang, Dawei Li, Shiping Yang, Yanran Li

摘要:

最近,预训练的基于transformer的模型在定义生成(DG)任务中取得了巨大的成功。然而,以前的编码器-解码器模型缺乏有效的表示学习来包含给定单词的完整语义成分,这导致生成不够具体的定义。为了解决这个问题,我们提出了一种新的对比学习方法,鼓励模型从定义序列编码中捕获更详细的语义表示。在三个主流基准上的实验结果表明,与现有的几种模型相比,该方法能够生成更具体、更高质量的定义。

英文摘要:

Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the given word, which leads to generating under-specific definitions. To address this problem, we propose a novel contrastive learning method, encouraging the model to capture more detailed semantic representations from the definition sequence encoding. According to both automatic and manual evaluation, the experimental results on three mainstream benchmarks demonstrate that the proposed method could generate more specific and high-quality definitions compared with several state-of-the-art models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑