Analysis Methods in Neural Language Processing: A Survey
arXiv:1812.08951
Abstract
The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new models have been proposed, many of which are thought to be opaque compared to their feature-rich counterparts. This has led researchers to analyze, interpret, and evaluate neural networks in novel and more fine-grained ways. In this survey paper, we review analysis methods in neural language processing, categorize them according to prominent research trends, highlight existing limitations, and point to potential directions for future work.
Version including the supplementary materials (3 tables), also available at https://boknilev.github.io/nlp-analysis-methods
References in corpus (5)
- Towards A Rigorous Science of Interpretable Machine Learning
- Understanding Neural Networks through Representation Erasure
- Towards Crafting Text Adversarial Samples
- From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
- Natural Language Multitasking: Analyzing and Improving Syntactic Saliency of Hidden Representations