DeepAI AI Chat
Log In Sign Up

Findings on Conversation Disentanglement

by   Rongxin Zhu, et al.
The University of Melbourne

Conversation disentanglement, the task to identify separate threads in conversations, is an important pre-processing step in multi-party conversational NLP applications such as conversational question answering and conversation summarization. Framing it as a utterance-to-utterance classification problem – i.e. given an utterance of interest (UOI), find which past utterance it replies to – we explore a number of transformer-based models and found that BERT in combination with handcrafted features remains a strong baseline. We then build a multi-task learning model that jointly learns utterance-to-utterance and utterance-to-thread classification. Observing that the ground truth label (past utterance) is in the top candidates when our model makes an error, we experiment with using bipartite graphs as a post-processing step to learn how to best match a set of UOIs to past utterances. Experiments on the Ubuntu IRC dataset show that this approach has the potential to outperform the conventional greedy approach of simply selecting the highest probability candidate for each UOI independently, indicating a promising future research direction.


page 1

page 2

page 3

page 4


Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer

Conversation structure is useful for both understanding the nature of co...

Automated Utterance Generation

Conversational AI assistants are becoming popular and question-answering...

Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterances

Meetings are a universal process to make decisions in business and proje...

Detecting Speaker Personas from Conversational Texts

Personas are useful for dialogue response prediction. However, the perso...

Conversation Disentanglement with Bi-Level Contrastive Learning

Conversation disentanglement aims to group utterances into detached sess...

A Hybrid Architecture for Multi-Party Conversational Systems

Multi-party Conversational Systems are systems with natural language int...

Action based Network for Conversation Question Reformulation

Conversation question answering requires the ability to interpret a ques...