Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization

Abstract

Text summarization is one of the most challenging and interesting problems in NLP. Although much attention has been paid to summarizing structured text like news reports or encyclopedia articles, summarizing conversations-an essential part of humanhuman/machine interaction where most important pieces of information are scattered across various utterances of different speakersremains relatively under-investigated. This work proposes a multi-view sequence-tosequence model by first extracting conversational structures of unstructured daily chats from different views to represent conversations and then utilizing a multi-view decoder to incorporate different views to generate dialogue summaries. Experiments on a large-scale dialogue summarization corpus demonstrated that our methods significantly outperformed previous state-of-the-art models via both automatic evaluations and human judgment. We also discussed specific challenges that current approaches faced with this task. We have publicly released our code at https://github.com/GT-SALT/ Multi-View-Seq2Seq.

Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

“…Such methods struggled with generating succinct, fluent, and natural summaries, especially when the key information needs to be aggregated from multiple first-person point-of-view utterances (Song et al, 2020). Abstractive conversation summarization overcomes these issues by designing hierarchical models , incorporating commonsense knowledge (Feng et al, 2020), or leveraging conversational structures like dialogue acts (Goo and Chen, 2018), key point sequences (Liu et al, 2019a), topic segments (Liu et al, 2019b; and stage developments (Chen and Yang, 2020). Some recent research has also utilized discourse relations as input features in classifiers to detect important content in conversations (Murray et al, 2006;Bui et al, 2009;Qin et al, 2017).…”

“…Discourse Relation Graph Utterances from different speakers do not occur in isolation; instead, they are related within the context of discourse (Murray et al, 2006;Qin et al, 2017), which has been shown effective for dialogue understanding like identifying the decisions in multi-party dialogues (Bui et al, 2009) and detecting salient content in email conversations (McKeown et al, 2007). Although current attention-based neural models are supposed to, or might implicitly, learn certain relations between utterances, they often struggle to focus on many informative utterances (Chen and Yang, 2020;Song et al, 2020) and fail to address long-range dependencies (Xu et al, 2020), especially when there are frequent interruptions. As a result, explicitly incorporating the discourse relations will help neural summarization models better encode the unstructured conversations and concentrate on the most salient utterances to generate more informative and less redundant summaries.…”

“…In order to summarize the unstructured and complex conversations, a growing body of research has been conducted, such as transferring document summarization methods to conversation settings (Shang et al, 2018;Gliwa et al, 2019), adopting hierarchical models , or incorporating conversation structures like topic segmentation (Liu et al, 2019b;Chen and Yang, 2020), dialogue acts (Goo and Chen, 2018), and conversation stages (Chen and Yang, 2020). However, current approaches still face challenges in terms of succinctness and faithfulness, as most prior studies (i) fail to explicitly model dependencies between utterances which can help identify salient portions of conversations (Bui et al, 2009), and (ii) lack structured representations to learn the associations between speakers, actions and events.…”

“…Chen and Yang, 2020) 45.56 52.13 44.68 22.30 25.58 22.03 44.70 50.82 43.29 BART (Lewis et al, 2020) 45.15 49.58 45.97 21.66 23.95 22.16 44.46 48.92 44.26 S-BART w. Discourse † 45.89 51.34 45.87 22.50 25.26 22.33 44.83 49.93 44.17 S-BART w. Action † 45.67 50.25 46.44 22.39 24.70 22.96 44.86 49.29 44.75 S-BART w. Discourse&Action † 46.07 51.13 46.24 22.60 25.11 22.81 45.00 49.82 44.47…”

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization

“…Dialogue summaries are useful for participants to recap salient information in the talk and for absentees to grasp the key points. As a result, several models have been recently proposed to summarize daily conversations (Gliwa et al, 2019;Chen and Yang, 2020), meeting transcripts (Zhu et al, 2020) and customer support conversations .…”