Improving Multi-Party Dialogue Discourse Parsing via Domain Integration
This work addresses the challenge of domain adaptation for dialogue discourse parsing, which is incremental as it builds on existing methods to enhance cross-domain generalization.
The paper tackled the problem of poor cross-domain performance in multi-party dialogue discourse parsing due to limited domain-specific annotated data, and improved generalization by integrating domain adaptation methods into a Transformer-based parser, achieving better performance on cross-domain samples.
While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict the dependency structure and relations between the elementary discourse units, and provide feature-rich structural information for downstream tasks. However, the existing corpora with dialogue discourse annotation are collected from specific domains with limited sample sizes, rendering the performance of data-driven approaches poor on incoming dialogues without any domain adaptation. In this paper, we first introduce a Transformer-based parser, and assess its cross-domain performance. We next adopt three methods to gain domain integration from both data and language modeling perspectives to improve the generalization capability. Empirical results show that the neural parser can benefit from our proposed methods, and performs better on cross-domain dialogue samples.