DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog

TL;DR

This paper introduces N-to-N question-answer pair extraction from customer service chatlogs, enabling more comprehensive knowledge base enrichment by capturing cross-utterance QA pairs, with new models and a benchmark for evaluation.

Contribution

It proposes a novel N-to-N QA extraction task, introduces generative/discriminative methods, and establishes a benchmark with evaluation metrics for dialogue-level QA extraction.

Findings

Models perform well on multiple datasets.

Extracted QA pairs reveal dialogue structure insights.

Proposed methods adapt across domains and languages.

Abstract

Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios. Prior work attempts to obtain 1-to-1 QA pairs from growing customer service chatlog, which fails to integrate the incomplete utterances from the dialog context for composite QA retrieval. In this paper, we propose N-to-N QA extraction task in which the derived questions and corresponding answers might be separated across different utterances. We introduce a suite of generative/discriminative tagging based methods with end-to-end and two-stage variants that perform well on 5 customer service datasets and for the first time setup a benchmark for N-to-N DialogQAE with utterance and session level evaluation metrics. With a deep dive into extracted QA pairs, we find that the relations between and inside the QA pairs can be indicators to analyze the dialogue structure, e.g. information seeking, clarification, barge-in and elaboration. We also show that the proposed models can adapt to different domains and languages, and reduce the labor cost of knowledge accumulation in the real-world product dialogue platform.