ERASER: A Benchmark to Evaluate Rationalized NLP Models
This addresses the problem of tracking progress in interpretable NLP for researchers, though it is incremental as it builds on existing datasets and tasks.
The authors tackled the lack of standardized evaluation for interpretable NLP models by proposing the ERASER benchmark, which includes multiple datasets with human-annotated rationales and new metrics to assess alignment and faithfulness of model rationales.
State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP that reveal the `reasoning' behind model outputs. But work in this direction has been conducted on different datasets and tasks with correspondingly unique aims and metrics; this makes it difficult to track progress. We propose the Evaluating Rationales And Simple English Reasoning (ERASER) benchmark to advance research on interpretable models in NLP. This benchmark comprises multiple datasets and tasks for which human annotations of "rationales" (supporting evidence) have been collected. We propose several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are (i.e., the degree to which provided rationales influenced the corresponding predictions). Our hope is that releasing this benchmark facilitates progress on designing more interpretable NLP systems. The benchmark, code, and documentation are available at https://www.eraserbenchmark.com/