Online Conversation Disentanglement with Pointer Networks
This addresses the difficulty of following and extracting information from concurrent online conversations, offering a more generalizable solution compared to existing dataset-specific methods.
The paper tackles the problem of disentangling interleaved online conversations by proposing an end-to-end online framework that avoids handcrafted features, achieving state-of-the-art performance on the Ubuntu IRC dataset in link and conversation prediction tasks.
Huge amounts of textual conversations occur online every day, where multiple conversations take place concurrently. Interleaved conversations lead to difficulties in not only following the ongoing discussions but also extracting relevant information from simultaneous messages. Conversation disentanglement aims to separate intermingled messages into detached conversations. However, existing disentanglement methods rely mostly on handcrafted features that are dataset specific, which hinders generalization and adaptability. In this work, we propose an end-to-end online framework for conversation disentanglement that avoids time-consuming domain-specific feature engineering. We design a novel way to embed the whole utterance that comprises timestamp, speaker, and message text, and proposes a custom attention mechanism that models disentanglement as a pointing problem while effectively capturing inter-utterance interactions in an end-to-end fashion. We also introduce a joint-learning objective to better capture contextual information. Our experiments on the Ubuntu IRC dataset show that our method achieves state-of-the-art performance in both link and conversation prediction tasks.