arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.09893cs.CL
收藏

基于注意的词级交互模型:知识库问答的关系检测

An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering

Institute of Electronics, Chinese Academy of Sciences(中国科学院电子学研究所);University of Chinese Academy of Sciences(中国科学院大学);University of Technology Sydney(悉尼科技大学)

Hongzhi Zhang, Guandong Xu, Xiao Liang, Tinglei Huang, Kun fu

摘要:

由于问句中关系表达式的高度变异性,关系检测在知识库问答中起着至关重要的作用。传统的深度学习方法遵循编码-比较范式,其中问题和候选关系被表示为向量以比较它们的语义相似性。最大或平均池化操作将词序列压缩成固定维的向量,成为信息的瓶颈。在本文中,我们建议学习基于注意力的问题和关系之间的词级交互,以缓解瓶颈问题。与传统模型相似,问题和关系首先表示为向量序列。然后,不是通过池化操作将序列合并到单个向量中,而是学习来自问题的单词与关系之间的软对齐。随后将对齐的字与卷积神经网络(CNN)进行比较,并最终合并比较结果。基于注意力的词级交互模型(ABWIM)通过在低层表征上进行比较,缓解了在比较之前将序列合并为固定维向量所造成的信息丢失问题。在SimpleQuestions和WebQuestions数据集上的实验结果表明,ABWIM达到了最先进的准确率,证明了其有效性。

英文摘要:

Relation detection plays a crucial role in Knowledge Base Question Answering (KBQA) because of the high variance of relation expression in the question. Traditional deep learning methods follow an encoding-comparing paradigm, where the question and the candidate relation are represented as vectors to compare their semantic similarity. Max- or average- pooling operation, which compresses the sequence of words into fixed-dimensional vectors, becomes the bottleneck of information. In this paper, we propose to learn attention-based word-level interactions between questions and relations to alleviate the bottleneck issue. Similar to the traditional models, the question and relation are firstly represented as sequences of vectors. Then, instead of merging the sequence into a single vector with pooling operation, soft alignments between words from the question and the relation are learned. The aligned words are subsequently compared with the convolutional neural network (CNN) and the comparison results are merged finally. Through performing the comparison on low-level representations, the attention-based word-level interaction model (ABWIM) relieves the information loss issue caused by merging the sequence into a fixed-dimensional vector before the comparison. The experimental results of relation detection on both SimpleQuestions and WebQuestions datasets show that ABWIM achieves state-of-the-art accuracy, demonstrating its effectiveness.

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。

↑