Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization
Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.
Code (1)
Tasks
Abstractive Dialogue SummarizationAbstractive Text SummarizationDocument SummarizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Annotating Shallow Discourse Relations in Twitter Conversations
We introduce our pilot study applying PDTB-style annotation to Twitter conversations. Lexically grounded coherence annotation for Twitter threads will enable detailed investigations of the discourse structure of conversa…
ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations
This paper aims to quantitatively evaluate the performance of ChatGPT, an interactive large language model, on inter-sentential relations such as temporal relations, causal relations, and discourse relations. Given ChatG…
Discourse ParsingIn-Context LearningLanguage ModelingLanguage Modelling+5Annotation of anaphoric relations and topic continuity in Japanese conversation
This paper proposes a basic scheme for annotating anaphoric relations in Japanese conversations. More specifically, we propose methods of (i) dividing discourse segments into meaningful units, (ii) identifying zero prono…
Neural Discourse Modeling of Conversations
Deep neural networks have shown recent promise in many language-related tasks such as the modeling of conversations. We extend RNN-based sequence to sequence models to capture the long range discourse across many turns o…
CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations
Discourse parsing is an important task useful for NLU applications such as summarization, machine comprehension, and emotion recognition. The current discourse parsing datasets based on conversations consists of written …
Discourse ParsingEmotion RecognitionReading Comprehension