DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog
This work addresses the need to efficiently build knowledge bases for customer service chatbots, though it is incremental as it extends prior 1-to-1 extraction to N-to-N scenarios.
The paper tackles the problem of extracting question-answer pairs from customer service chatlogs, where questions and answers can be spread across multiple utterances, and introduces methods that perform well on 5 datasets, establishing a benchmark for this task.
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.