Unsupervised Conversation Disentanglement through Co-Training

TL;DR

This paper introduces an unsupervised deep co-training approach for conversation disentanglement, effectively separating interleaved messages into sessions without relying on human annotations, and improves downstream response selection.

Contribution

It proposes a novel unsupervised co-training method with two neural networks for conversation disentanglement, reducing dependence on annotated data and enhancing downstream task performance.

Findings

Achieves competitive results on Movie Dialogue Dataset

Enables training without human-annotated datasets

Improves multi-party response selection performance

Abstract

Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon human-annotated datasets, which are expensive to obtain in practice. In this work, we explore to train a conversation disentanglement model without referencing any human annotations. Our method is built upon a deep co-training algorithm, which consists of two neural networks: a message-pair classifier and a session classifier. The former is responsible for retrieving local relations between two messages while the latter categorizes a message to a session by capturing context-aware information. Both networks are initialized respectively with pseudo data built from an unannotated corpus. During the deep co-training process, we use the session classifier as a reinforcement learning component to learn a session assigning policy by maximizing the local rewards given by the message-pair classifier. For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier. Experimental results on the large Movie Dialogue Dataset demonstrate that our proposed approach achieves competitive performance compared to the previous supervised methods. Further experiments show that the predicted disentangled conversations can promote the performance on the downstream task of multi-party response selection.