谁回应谁：会话结构中潜在话题和话语的共同作用
Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure
摘要：
每天都会产生大量的在线对话，因此迫切需要理解对话。作为构建讨论的基础，我们识别了会话话语中的回应关系，这些关系将回应话语与其启动联系起来。为了弄清楚谁回应谁，在这里，我们探讨如何主题内容的一致性和话语角色的依赖性表明这样的互动，而大多数以前的工作忽略了潜在因素的影响，潜在的单词出现。我们提出了一个模型来学习潜在的主题和话语分布，并预测成对的启动-响应链接，通过利用主题一致性和话语依赖。对中英文会话的实验结果表明，我们的模型明显优于先前的艺术状态，如79对73 MRR的中文客户服务对话。我们进一步探讨我们的输出，并阐明如何主题和话语表明会话用户交互。
英文摘要：
Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts, such as 79 vs. 73 MRR on Chinese customer service dialogues. We further probe into our outputs and shed light on how topics and discourse indicate conversational user interactions.
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。
