Multi-tasking Dialogue Comprehension with Discourse Parsing

Multi-tasking Dialogue Comprehension with Discourse Parsing Yuchen He1,2,3,#, Zhuosheng Zhang1,2,3,#, Hai Zhao1,2,3,∗ 1 Department of Computer Science and Engineering, Shanghai Jiao Tong University 2 Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University 3MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University {21644h,zhangzs}@sjtu.edu.cn,zhaohai@cs.sjtu.edu.cn Abstract Multi-party dialogue machine reading compre- hension (MRC) raises an even more challeng- ing understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC. To accu- rately perform the question-answering (QA) task according to such multi-party dialogue, models have to handle fundamentally differ- ent discourse relationships from common non- dialogue plain text, where discourse relations are supposed to connect two far apart utter- ances in a linguistics-motivated way. To fur- ther explore the role of such unusual discourse structure on the correlated QA task in terms of MRC, we propose the first multi-task model for jointly performing QA and discourse parsing (DP) on the multi-party dialogue MRC task. Our proposed model is evaluated on the latest benchmark Molweni, whose results indicate that training with complementary tasks indeed benefits not only QA task, but also DP task itself. We further find that the joint model is distinctly stronger when handling longer dia- logues which again verifies the necessity of DP in the related MRC. 1 Introduction Machine reading comprehension (MRC) is essen- tially formed as a question-answering (QA) task sub- ject to a given context like passages (Hermann et al., 2015; Rajpurkar et al., 2016). Recently, more and ∗Corresponding author. # Equal contribution. This paper was partially supported by Key Projects of National Natural Science Foundation of China (U1836222 and 61733011). more attention is raised on a special MRC type whose given context is a dialogue text (Reddy et al., 2019; Choi et al., 2018). Training machines to understand dialogue has been shown more challenging than the common MRC as every utterance in dialogue has an additional property of speaker role, which breaks the continuity as that in common non-dialogue texts due to the presence of crossing dependencies which are commonplace in multi-party chat (Allen et al., 1994; Perez and Liu, 2017). Thus dialogue demonstrates quite a different discourse relationship mode from the non-dialogue in that consecutive utterances usu- ally have a type of discourse relation (Afantenos et al., 2015; Shi and Huang, 2019; Li et al., 2020; Li et al., 2021). Recently, there emerges an even more challenging dialogue MRC task, the multi-party one, which involves more than two speakers in the given dialogue passage (Li et al., 2020; Li et al., 2021) and further demonstrates unusual discourse struc- tures such as quite a lot of adjacent utterances do not have any semantic relationship. Being harder for comprehension, multi-party dialogue MRC has a great value of application which can be applied to frontiers such as intelligent human-computer inter- face and knowledge graph building. As shown in Figure 1, our work tries to extract the answer to the given question …

Content truncated to 500 words