解决对话查询生成中因过度关联导致的漏提与误提问题
Mitigating the Negative Impact of Over-association for Conversational Query Production
- 通过实例级加权策略缓解标注时的背景知识过度联想
- 在两个数据集上提升2%-5%性能，概念选择更准确
- 适合需要高效利用少量标注数据的对话系统研究者
对话查询生成旨在从对话历史中生成搜索查询，以帮助基于知识的对话系统获取相关信息。现有模型因最大化黄金查询的似然而面临数据饥渴问题，推理时易遗漏重要概念或生成无关概念。我们归因于‘过度关联’现象：大量黄金查询虽与对话主题间接相关，但因标注者无意识使用背景知识所致。本文细致分析该现象对预训练序列到序列查询生成器的负面影响，并提出多角度实例级加权训练策略进行缓解。在Wizard-of-Internet和DuSinc两个基准上的实验表明，所提方法有效减轻负面影响，带来显著性能提升（自动指标与人工评估均提高2%-5%）。进一步分析显示，模型能更好选取对话历史中的关键概念，且数据效率比基线高10倍。代码已公开于https://github.com/DeepLearnXMU/QG-OverAsso。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。