Topic-Aware Pointer-Generator Networks for Summarizing Spoken Conversations

• Published in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) pp. 814 - 821
• Main Authors: Liu, Zhengyuan, Ng, Angela, Lee, Sheldon, Aw, Ai Ti, Chen, Nancy F.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-12-2019
• Subjects: attention mechanism; Context modeling; conversation technology; Decoding; Dialogue; Hospitals; Linguistics; Mathematical model; neural networks; summarization; Task analysis; Vocabulary
• DOI: 10.1109/ASRU46091.2019.9003764

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.