Instance-Based Neural Dependency Parsing
arXiv:2109.13497
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.
arXiv comment15 pages, accepted to TACL 2021
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- On the difficulty of training Recurrent Neural Networks
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- How to Explain Individual Classification Decisions
- A Survey on Metric Learning for Feature Vectors and Structured Data
- REALM: Retrieval-Augmented Language Model Pre-Training
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- MBT: A Memory-Based Part of Speech Tagger-Generator
- Model Agnostic Supervised Local Explanations
- Memory-Based Shallow Parsing
- Nearest Neighbor Machine Translation