Text Characterization Toolkit

TL;DR

The paper introduces a toolkit for in-depth analysis of NLP datasets and models, addressing biases and artifacts often overlooked by standard performance metrics.

Contribution

It provides an accessible annotation tool and analysis scripts to study dataset properties and their impact on model behavior, promoting deeper evaluation practices.

Findings

Identification of dataset biases and heuristics

Analysis of difficult examples for models

Case studies across three domains

Abstract

In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that - especially given the well-known fact that benchmarks often contain biases, artefacts, and spurious correlations - deeper results analysis should become the de-facto standard when presenting new models or benchmarks. We present a tool that researchers can use to study properties of the dataset and the influence of those properties on their models' behaviour. Our Text Characterization Toolkit includes both an easy-to-use annotation tool, as well as off-the-shelf scripts that can be used for specific analyses. We also present use-cases from three different domains: we use the tool to predict what are difficult examples for given well-known trained models and identify (potentially harmful) biases and heuristics that are present in a dataset.