Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards

TL;DR

This paper introduces a neural network model that jointly performs coreference resolution and semantic role labeling, using reinforcement learning to enhance global document coherence and improve performance across multiple datasets.

Contribution

It proposes a novel joint architecture with coherence-based reinforcement learning to better capture document-level semantics in NLP tasks.

Findings

Improved accuracy on coreference resolution and semantic role labeling tasks.

Enhanced global coherence in semantic annotations across datasets.

Applicable across various encoder architectures.

Abstract

Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, and what semantic roles expressions serve in the sentence. However, they are often closely interdependent, and both generally necessitate natural language understanding. Do they form a coherent abstract representation of documents? We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the 'coherence' of the combined shallow semantic graph. Using the resulting coherence score as a reward for our joint semantic analyzer, we use reinforcement learning to encourage global coherence over the document and between semantic annotations. This leads to improvements on both tasks in multiple datasets from different domains, and across a range of encoders of different expressivity, calling, we believe, for a more holistic approach to semantics in NLP.