Intra-Correlation Encoding for Chinese Sentence Intention Matching

Proceedings of the 28th International Conference on Computational Linguistics, pages 5193–5204 Barcelona, Spain (Online), December 8-13, 2020 5193 Intra-Correlation Encoding for Chinese Sentence Intention Matching Xu Zhang1, Yifeng Li2, Wenpeng Lu1∗, Ping Jian3, Guoqiang Zhang4 1School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China 2Department of Computer Science, Brock University, Niagara Region, Canada 3School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 4Centre for Audio, Acoustics and Vibration, University of Technology Sydney, Sydney, Australia xuzhang.p@foxmail.com, yli2@brocku.ca, lwp@qlu.edu.cn, pjian@bit.edu.cn, guoqiang.zhang@uts.edu.au Abstract Sentence intention matching is vital for natural language understanding. Especially for Chinese sentence intention matching task, due to the ambiguity of Chinese words, se- mantic missing or semantic confusion are more likely to occur in the encoding process. Although the existing methods have enriched text representation through pre-trained word embedding to solve this problem, due to the particularity of Chinese text, differ- ent granularities of pre-trained word embedding will affect the semantic description of a piece of text. In this paper, we propose an effective approach that combines character- granularity and word-granularity features to perform sentence intention matching, and we utilize soft alignment attention to enhance the local information of sentences on the corresponding levels. The proposed method can capture sentence feature information from multiple perspectives and correlation information between different levels of sen- tences. By evaluating on BQ and LCQMC datasets, our model has achieved remarkable results, and demonstrates better or comparable performance with BERT-based models. 1 Introduction As a branch of sentence semantic matching (SSM), sentence intention matching (SIM) is critical to question answering systems in certain applications. In general, SSM is to judge whether two sentences express the same meaning. However, in a question answering system, SIM intends to determine whether two questions share the same intention and could be addressed by the same answer, which is more challenging than other SSM tasks. As an example shown in Table 1, although both sentences in Q1 and Q2 share similar intention in fact, it is difficult to distinguish whether they are similar at the semantic intention level without considering the deep context. With the development of deep learning, a series of SSM models are proposed for semantic matching tasks (Wang et al., 2017; Gong et al., 2018; Huang et al., 2019; Li et al., 2019; Liu et al., 2020). However, these models simply consider the characteristics of the semantic level of the text but overlook the deep intentional features. Researchers have attempted to extract deeper semantic features through attention mechanisms (Tan et al., 2018; Tay et al., 2018), memory networks (Cheng et al., 2016), as well as the addition of external syntactic structures and lexical datasets as in WordNet (Chen et al., 2017). Although the above methods obtain deep semantic features from different perspectives, they cannot completely overcome the feature missing phenomenon in the encoding process. Especially due to the diversity of Chinese semantic features, the above existing methods cannot better capture complicated deep semantic features. ∗Corresponding Author: …

Content truncated to 500 words