Topic Spotting using Hierarchical Networks with Self Attention
This work addresses the challenge of making dialogue systems more engaging and efficient for users, though it is incremental as it builds on existing deep learning techniques for topic spotting.
The authors tackled the problem of topic spotting in conversations to improve dialogue systems, proposing a hierarchical model with self-attention that outperformed previous methods on the Switchboard corpus and showed strong generalization in online settings.
Success of deep learning techniques have renewed the interest in development of dialogue systems. However, current systems struggle to have consistent long term conversations with the users and fail to build rapport. Topic spotting, the task of automatically inferring the topic of a conversation, has been shown to be helpful in making a dialog system more engaging and efficient. We propose a hierarchical model with self attention for topic spotting. Experiments on the Switchboard corpus show the superior performance of our model over previously proposed techniques for topic spotting and deep models for text classification. Additionally, in contrast to offline processing of dialog, we also analyze the performance of our model in a more realistic setting i.e. in an online setting where the topic is identified in real time as the dialog progresses. Results show that our model is able to generalize even with limited information in the online setting.