Instance-Based Neural Dependency Parsing

TL;DR

This paper introduces neural dependency parsing models that use instance-based inference, enabling interpretability by comparing predicted edges to training set edges, achieving competitive accuracy and understandable explanations.

Contribution

It presents a novel instance-based neural dependency parser that enhances interpretability without sacrificing accuracy.

Findings

Achieves competitive accuracy with standard neural models

Provides plausible and interpretable explanations for predictions

Demonstrates the effectiveness of instance-based inference in dependency parsing

Abstract

Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.