Existing conversational models are handled by a database(DB) and API based systems. However, very often users' questions require information that cannot be handled by such systems. Nonetheless, answers to these questions are available in the form of customer reviews and FAQs. DSTC-11 proposes a three stage pipeline consisting of knowledge seeking turn detection, knowledge selection and response generation to create a conversational model grounded on this subjective knowledge. In this paper, we focus on improving the knowledge selection module to enhance the overall system performance. In particular, we propose entity retrieval methods which result in an accurate and faster knowledge search. Our proposed Named Entity Recognition (NER) based entity retrieval method results in 7X faster search compared to the baseline model. Additionally, we also explore a potential keyword extraction method which can improve the accuracy of knowledge selection. Preliminary results show a 4 \% improvement in exact match score on knowledge selection task. The code is available https://github.com/raja-kumar/knowledge-grounded-TODS
翻译:现有的对话建模系统都是基于数据库(DB)和API的。 然而,很多用户的问题需要一些无法由这些系统处理的信息。 尽管如此,这些问题的答案以客户评价和常见问题解答的形式提供。 DSTC-11提出了一个由寻求知识的交互识别,知识选择和响应生成三个阶段构成的流程,以此在主观知识基础上创建对话模型。 在本文中,我们关注于改进知识选择模块以提高整个系统的性能。 特别是,我们提出了实体检索方法,以实现准确且更快的知识搜索。 我们提出的基于命名实体识别(NER)的实体检索方法相比基线模型结果快了7倍。 此外,我们还探讨了一种可能改进知识选择准确性的关键字提取方法。 初步结果显示,在知识选择任务上证明了4%的精确匹配分数提高。 代码可在 https://github.com/raja-kumar/knowledge-grounded-TODS 上找到。