The ability to monitor the evolution of topics over time is extremely
valuable for businesses. Currently, all existing topic tracking methods use
lexical information by matching word usage. However, no studies has ever
experimented with the use of semantic information for tracking topics. Hence,
we explore a novel semantic-based method using word embeddings. Our results
show that a semantic-based approach to topic tracking is on par with the
lexical approach but makes different mistakes. This suggest that both methods
may complement each other.

本研究探讨了使用词嵌入的语义信息进行话题追踪的方法可行性。结果表明，这种语义方法与基于词汇的方法相当，但会出现不同的错误，两种方法可能互补。

利用意义而非词汇来追踪话题

Using meaning instead of words to track topics

While participants in a multi-party multi-turn conversation simultaneously
engage in multiple conversation topics, existing response selection methods are
developed mainly focusing on a two-party single-conversation scenario. Hence,
the prolongation and transition of conversation topics are ignored by current
methods. In this work, we frame response selection as a dynamic topic tracking
task to match the topic between the response and relevant conversation context.
With this new formulation, we propose a novel multi-task learning framework
that supports efficient encoding through large pretrained models with only two
utterances at once to perform dynamic topic disentanglement and response
selection. We also propose Topic-BERT an essential pretraining step to embed
topic information into BERT with self-supervised learning. Experimental results
on the DSTC-8 Ubuntu IRC dataset show state-of-the-art results in response
selection and topic disentanglement tasks outperforming existing methods by a
good margin.

这项研究通过动态主题跟踪任务将回复选择作为一种新的表述方法，并提出了一种支持高效编码的新型多任务学习框架，并且通过预训练模型，仅使用两次讲话来进行动态主题分离和回复选择。同时，还提出了 Topic-BERT 的关键预训练步骤来嵌入主题信息，并在 DSTC-8 Ubuntu IRC 数据集上获得了表现出色的结果。