Topic-Aware Pointer-Generator Networks for Summarizing Spoken Conversations
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 814-821
Abstract
Due to the lack of publicly available resources, conversation summarization has received far less attention than text summarization. As the purpose of conversations is to exchange information between at least two interlocutors, key information about a certain topic is often scattered and spanned across multiple utterances and turns from different speakers. This phenomenon is more pronounced during spoken conversations, where speech characteristics such as backchanneling and false-starts might interrupt the topical flow. Moreover, topic diffusion and (intra-utterance) topic drift are also more common in human-to-human conversations. Such linguistic characteristics of dialogue topics make sentence-level extractive summarization approaches used in spoken documents ill-suited for summarizing conversations. Pointer-generator networks have effectively demonstrated its strength at integrating extractive and abstractive capabilities through neural modeling in text summarization. To the best of our knowledge, to date no one has adopted it for summarizing conversations. In this work, we propose a topic-aware architecture to exploit the inherent hierarchical structure in conversations to further adapt the pointer-generator model. Our approach significantly outperforms competitive baselines, achieves more efficient learning outcomes, and attains more robust performance.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Summarizing a Document by Trimming the Discourse TreeIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Effective Approaches to Attention-based Neural Machine Translation2015
- A Neural Attention Model for Abstractive Sentence Summarization2015
- Improving the Estimation of Word Importance for News Multi-Document Summarization2014
- Glove: Global Vectors for Word Representation2014
- Automatic Text Summarization: Past, Present and Future2012
- Improving supervised learning for meeting summarization using sampling and regressionComputer Speech & Language, 2010
- Customization in a unified framework for summarizing medical literatureArtificial Intelligence in Medicine, 2005
- The decomposition of human-written summary sentences1999
- Long Short-Term MemoryNeural Computation, 1997