Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling

TLDR

In customer service, dialogue summarization can boost efficiency by automatically summarizing long spoken dialogues, but noise, common semantics, and role‑specific information make general topic modeling difficult. The study aims to develop a topic‑oriented summarizer that produces highly abstractive summaries preserving the main ideas from customer service dialogues. We propose a two‑stage summarizer (TDS) that jointly uses a saliency‑aware neural topic model (SATM) to capture multi‑role information for topic‑oriented summarization. Experiments on a real‑world Chinese customer service dataset show our method outperforms several strong baselines.

Abstract

In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics. In this work, we focus on topic-oriented dialogue summarization, which generates highly abstractive summaries that preserve the main ideas from dialogues. In spoken dialogues, abundant dialogue noise and common semantics could obscure the underlying informative content, making the general topic modeling approaches difficult to apply. In addition, for customer service, role-specific information matters and is an indispensable part of a summary. To effectively perform topic modeling on dialogues and capture multi-role information, in this work we propose a novel topic-augmented two-stage dialogue summarizer (TDS) jointly with a saliency-aware neural topic model (SATM) for topic-oriented summarization of customer service dialogues. Comprehensive studies on a real-world Chinese customer service dataset demonstrated the superiority of our method against several strong baselines.