Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts
By Chih-Wen Goo, Yun-Nung (Vivian) Chen. 2018
133 citations recorded by the source corpus.
Neural abstractive summarization has been increasingly studied, where the prior work mainly focused on summarizing single-speaker documents (news, scientific publications, etc). In dialogues, there are diverse interactive patterns between speakers, which are usually defined as dialogue acts. The interactive signals may provide informative cues for better summarizing dialogues. This paper proposes to explicitly leverage dialogue acts in a neural summarization model, where a sentence-gated mechanism is designed for modeling the relationships between dialogue acts and the summary. The experiments show that our proposed model significantly improves the abstractive summarization performance compared to the state-of-the-art baselines on the AMI meeting corpus, demonstrating the usefulness of the interactive signal provided by dialogue acts.1
Subfields: Artificial Intelligence, Summarization, Dialogue & Conversational AI
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yang Liu
- Jason Aaron Edward Weston
- Mohit Bansal
- Arthur Szlam
- Yoav Goldberg
- Kyunghyun Cho
- Yue Zhang
- Noah A. Smith
In Summarization
In Dialogue & Conversational AI
- Jason Aaron Edward Weston
- Jing Xu
- Iwona Mochol
- Aleksander Wawer
- Bogdan Gliwa
- Maciej Biesek
- Arthur Szlam
- Kurt Shuster
Citations in the corpus
- SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization (2019, methodology): “Since the corpus has a low number of summaries (for 141 dialogues), Goo and Chen (2018) proposed to use assigned topic descriptions as gold references.”
- Beyond Goldfish Memory: Long-Term Open-Domain Conversation (2021, background): “…focuses on summarizing documents (Kaikhah, 2004; Kry´s-1 ci´nski et al., 2019; Cheng and Lapata, 2016), for example summarizing in order to predict other relevant information (West et al., 2019), and there is some work on dialogue as well (Goo and Chen, 2018; Gliwa et al., 2019; Pan et al., 2018).”
- DialogSum: A Real-Life Scenario Dialogue Summarization Dataset (2021, result): “…important word-level information from dialogues in D IALOG S UM , while U NI LM V 2 BASE shows better performance on clause-level — it can identify the speakers and partially preserve coreference information, consistent with findings of Levesque et al. (2012) to summarize (Goo and Chen, 2018).”