A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge
This work addresses the challenge of improving conversational AI systems for information retrieval, though it is incremental as it builds on existing models like RoBERTa and ELECTRA.
The authors tackled the problem of selecting clarifying questions in conversational information retrieval by proposing a system with response understanding, candidate question recalling, and ranking, which achieved top scores in document relevance metrics and best recall@[20,30] in question relevance tasks.
This paper presents the participation of NetEase Game AI Lab team for the ClariQ challenge at Search-oriented Conversational AI (SCAI) EMNLP workshop in 2020. The challenge asks for a complete conversational information retrieval system that can understanding and generating clarification questions. We propose a clarifying question selection system which consists of response understanding, candidate question recalling and clarifying question ranking. We fine-tune a RoBERTa model to understand user's responses and use an enhanced BM25 model to recall the candidate questions. In clarifying question ranking stage, we reconstruct the training dataset and propose two models based on ELECTRA. Finally we ensemble the models by summing up their output probabilities and choose the question with the highest probability as the clarification question. Experiments show that our ensemble ranking model outperforms in the document relevance task and achieves the best recall@[20,30] metrics in question relevance task. And in multi-turn conversation evaluation in stage2, our system achieve the top score of all document relevance metrics.