Instance-Based Neural Dependency Parsing

doi:10.1162/tacl_a_00439

Instance-Based Neural Dependency Parsing

2021-12-17

2

OA

AI

DOI：10.1162/tacl_a_00439

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

CLASSIFICATION

MODEL

Instance-Based Neural Dependency Parsing

Abstract

Journal

Organization