The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
arXiv:2008.05122
Abstract
We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it perform poorly? What happens under a controlled change in the input? LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis. We include case studies for a diverse set of workflows, including exploring counterfactuals for sentiment analysis, measuring gender bias in coreference systems, and exploring local behavior in text generation. LIT supports a wide range of models--including classification, seq2seq, and structured prediction--and is highly extensible through a declarative, framework-agnostic API. LIT is under active development, with code and full documentation available at https://github.com/pair-code/lit.
References in corpus (13)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Semantics derived automatically from language corpora contain human-like biases
- Axiomatic Attribution for Deep Networks
- Teaching Machines to Read and Comprehend
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- The What-If Tool: Interactive Probing of Machine Learning Models
- InterpretML: A Unified Framework for Machine Learning Interpretability
- Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
- Embedding Projector: Interactive Visualization and Interpretation of Embeddings
- FairSight: Visual Analytics for Fairness in Decision Making