Entity-Aware Biaffine Attention Model for Improved Constituent Parsing with Reduced Entity Violations

TL;DR

This paper introduces an entity-aware biaffine attention model for constituent parsing that reduces entity violations, improves accuracy, and introduces a new metric EVR, demonstrating effectiveness across multiple datasets and downstream tasks.

Contribution

The paper presents a novel entity-aware biaffine attention model that incorporates entity information to reduce violations and improve parsing accuracy.

Findings

Lowest Entity Violating Rate (EVR) achieved on datasets

Maintains high precision, recall, and F1-scores

Effective in downstream sentiment analysis tasks

Abstract

Constituency parsing involves analyzing a sentence by breaking it into sub-phrases, or constituents. While many deep neural models have achieved state-of-the-art performance in this task, they often overlook the entity-violating issue, where an entity fails to form a complete sub-tree in the resultant parsing tree. To address this, we propose an entity-aware biaffine attention model for constituent parsing. This model incorporates entity information into the biaffine attention mechanism by using additional entity role vectors for potential phrases, which enhances the parsing accuracy. We introduce a new metric, the Entity Violating Rate (EVR), to quantify the extent of entity violations in parsing results. Experiments on three popular datasets-ONTONOTES, PTB, and CTB-demonstrate that our model achieves the lowest EVR while maintaining high precision, recall, and F1-scores comparable to existing models. Further evaluation in downstream tasks, such as sentence sentiment analysis, highlights the effectiveness of our model and the validity of the proposed EVR metric.