通过无监督联合建模实现查询增强的知识密集型对话
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
AI总结：
本文提出无监督查询增强方法 QKConv，通过联合训练查询生成器、知识选择器和响应生成器，仅利用对话上下文与目标响应，在三个知识密集型对话数据集上优于所有无监督方法并接近有监督方法。
摘要：
本文提出了一种用于知识密集型对话的无监督查询增强方法，名为 QKConv。QKConv 包含三个模块：查询生成器、现成的知识选择器和响应生成器。QKConv 通过联合训练进行优化，在生成响应时探索多个候选查询并利用相应选择的知识。联合训练仅依赖对话上下文和目标响应，无需额外的查询标注或知识来源标注。为评估所提出的 QKConv 的有效性，我们在三个具有代表性的知识密集型对话数据集上进行了实验：对话式问答、任务型对话和知识 grounding 对话。实验结果表明，QKConv 在三个数据集上的表现优于所有无监督方法，并且与有监督方法相比取得了具有竞争力的性能。
英文摘要：
In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge. The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances. To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledge-intensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
