Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues

TL;DR

This paper introduces a graph-based framework to model causal relations in collaborative dialogues, focusing on probing questions that elicit responses, and demonstrates its effectiveness on two challenging datasets.

Contribution

It presents a novel approach to modeling deliberation chains as a coreference-style clustering problem in collaborative dialogue analysis.

Findings

Outperforms baseline models in identifying causal relations.

Effectively models probing and causal utterances jointly.

Establishes a new standard for this task on two datasets.

Abstract

Question-asking in collaborative dialogue has long been established as key to knowledge construction, both in internal and collaborative problem solving. In this work, we examine probing questions in collaborative dialogues: questions that explicitly elicit responses from the speaker's interlocutors. Specifically, we focus on modeling the causal relations that lead directly from utterances earlier in the dialogue to the emergence of the probing question. We model these relations using a novel graph-based framework of deliberation chains, and reframe the problem of constructing such chains as a coreference-style clustering problem. Our framework jointly models probing and causal utterances and the links between them, and we evaluate on two challenging collaborative task datasets: the Weights Task and DeliData. Our results demonstrate the effectiveness of our theoretically-grounded approach compared to both baselines and stronger coreference approaches, and establish a standard of performance in this novel task.