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 2204.11673cs.IRcs.AI
收藏

基于预训练语言模型的显式知识挖掘

Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking

University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)

Qian Dong, Yiding Liu, Suqi Cheng, Shuaiqiang Wang, Zhicong Cheng, Shuzi Niu, Dawei Yin

摘要:

段落重排序是在检索阶段获得的候选段落集上进行排列。由于预训练语言模型在自然语言理解方面的巨大优势,重新排序器得到了蓬勃发展。然而,现有的基于PLM的重排序器可能容易遭受词汇不匹配和缺乏领域特定知识的困扰。为了缓解这些问题,显式知识包含在知识图谱在我们的工作中仔细介绍。具体而言,我们采用现有的知识图谱,这是不完整的和嘈杂的,并首次将其应用于通道重排序任务。为了利用可靠的知识,我们提出了一种新的知识图谱蒸馏方法,并获得知识Meta图作为查询和通道之间的桥梁。为了在潜在空间中对齐这两种嵌入,我们采用PLM作为文本编码器,知识Meta图上的图神经网络作为知识编码器。此外,还设计了一种新的知识注入器,实现了文本与知识编码器的动态交互。实验结果表明,我们的方法的有效性,特别是在查询需要深入的领域知识。

英文摘要:

Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural language understanding. However, existing PLM based re-rankers may easily suffer from vocabulary mismatch and lack of domain specific knowledge. To alleviate these problems, explicit knowledge contained in knowledge graph is carefully introduced in our work. Specifically, we employ the existing knowledge graph which is incomplete and noisy, and first apply it in passage re-ranking task. To leverage a reliable knowledge, we propose a novel knowledge graph distillation method and obtain a knowledge meta graph as the bridge between query and passage. To align both kinds of embedding in the latent space, we employ PLM as text encoder and graph neural network over knowledge meta graph as knowledge encoder. Besides, a novel knowledge injector is designed for the dynamic interaction between text and knowledge encoder. Experimental results demonstrate the effectiveness of our method especially in queries requiring in-depth domain knowledge.

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。

↑