Mitigating the Negative Impact of Over-association for Conversational Query Production
This work addresses a specific issue in knowledge-based dialogue systems, offering an incremental improvement for generating more accurate search queries from conversations.
The paper tackles the problem of conversational query generation, where models trained on gold queries suffer from dropping important concepts and generating irrelevant ones due to over-association in the data. The proposed instance-level weighting strategies lead to significant performance gains of 2%-5% across metrics and improve data efficiency by 10 times.
Conversational query generation aims at producing search queries from dialogue histories, which are then used to retrieve relevant knowledge from a search engine to help knowledge-based dialogue systems. Trained to maximize the likelihood of gold queries, previous models suffer from the data hunger issue, and they tend to both drop important concepts from dialogue histories and generate irrelevant concepts at inference time. We attribute these issues to the over-association phenomenon where a large number of gold queries are indirectly related to the dialogue topics, because annotators may unconsciously perform reasoning with their background knowledge when generating these gold queries. We carefully analyze the negative effects of this phenomenon on pretrained Seq2seq query producers and then propose effective instance-level weighting strategies for training to mitigate these issues from multiple perspectives. Experiments on two benchmarks, Wizard-of-Internet and DuSinc, show that our strategies effectively alleviate the negative effects and lead to significant performance gains (2%-5% across automatic metrics and human evaluation). Further analysis shows that our model selects better concepts from dialogue histories and is 10 times more data efficient than the baseline. The code is available at https://github.com/DeepLearnXMU/QG-OverAsso.