arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.08205cs.CL
收藏

利用背景知识构建会话系统

Towards Exploiting Background Knowledge for Building Conversation Systems

Indian Institute of Technology Madras(马德拉斯印度理工学院)

Nikita Moghe, Siddhartha Arora, Suman Banerjee, Mitesh M. Khapra

摘要:

现有的对话数据集包含一系列的话语和响应,而没有任何明确的背景知识与它们相关联。这导致了模型的发展,这些模型将对话视为序列到序列生成任务(即,给定话语序列生成响应序列)。这不仅是一种过于简单化的对话观点,而且与人类严重依赖关于主题的背景知识(而不是简单地依赖先前的话语序列)的对话方式截然不同。例如,人类通常(不自觉地)产生从他们已经阅读的关于主题的背景文章复制或适当修改的话语。为了促进这种模仿人类对话过程的自然对话模型的开发,我们创建了一个包含电影聊天的新数据集,其中每个响应都是通过复制和/或修改来自非结构化背景知识(例如关于电影的情节,评论和评论)的句子来显式生成的。我们使用三种不同的模型在该数据集(来自9 K对话的90 K话语)上建立基线结果:(i)基于纯生成的模型,其忽略背景知识;(ii)基于生成的模型,其在需要时学习从背景知识复制信息;以及(iii)基于跨度预测的模型,其预测背景知识中的适当响应跨度。

英文摘要:

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence generation task i.e, given a sequence of utterances generate the response sequence). This is not only an overly simplistic view of conversation but it is also emphatically different from the way humans converse by heavily relying on their background knowledge about the topic (as opposed to simply relying on the previous sequence of utterances). For example, it is common for humans to (involuntarily) produce utterances which are copied or suitably modified from background articles they have read about the topic. To facilitate the development of such natural conversation models which mimic the human process of conversing, we create a new dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie. We establish baseline results on this dataset (90K utterances from 9K conversations) using three different models: (i) pure generation based models which ignore the background knowledge (ii) generation based models which learn to copy information from the background knowledge when required and (iii) span prediction based models which predict the appropriate response span in the background knowledge.

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。

↑