Explainability of Text Processing and Retrieval Methods: A Survey

TL;DR

This survey reviews recent research on making deep learning models for text processing and retrieval more transparent and interpretable, covering methods like word embeddings, transformers, and BERT.

Contribution

It provides a comprehensive overview of explainability techniques applied to NLP and IR models, highlighting current approaches and future research directions.

Findings

Various explainability methods for word embeddings and sequence models

Insights into attention mechanisms and transformer interpretability

Identification of gaps and future challenges in model transparency

Abstract

Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview of research on the explainability and interpretability of natural language processing and information retrieval methods. More specifically, we survey approaches that have been applied to explain word embeddings, sequence modeling, attention modules, transformers, BERT, and document ranking. The concluding section suggests some possible directions for future research on this topic.