Online Conversation Disentanglement with Pointer Networks

TL;DR

This paper introduces an end-to-end online framework using pointer networks for conversation disentanglement, effectively separating interleaved online messages without relying on handcrafted features.

Contribution

It proposes a novel embedding and attention mechanism for online disentanglement, improving generalization and achieving state-of-the-art results.

Findings

State-of-the-art performance on Ubuntu IRC dataset

Effective modeling of inter-utterance interactions

End-to-end approach without handcrafted features

Abstract

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.