Instance-Based Neural Dependency Parsing
This work addresses the need for interpretable rationales in dependency parsing for NLP practitioners, though it is incremental as it builds on existing neural methods.
The paper tackled the problem of interpretability in neural dependency parsing by developing instance-based models that compare input edges to training examples, achieving competitive accuracy with standard neural models.
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.