MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
This toolkit addresses the need for comprehensive evaluation strategies beyond traditional metrics for researchers and engineers working on machine translation, though it is incremental as it builds upon existing frameworks.
The authors tackled the problem of limited evaluation capabilities for machine translation systems by introducing MT-LENS, a toolkit that extends LM-eval-harness to assess translation quality, gender bias, added toxicity, and robustness to misspellings, resulting in a user-friendly platform with interactive visualizations for comparing systems and analyzing translations.
We introduce MT-LENS, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-LENS addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluation metrics. It also offers a user-friendly platform to compare systems and analyze translations with interactive visualizations. MT-LENS aims to broaden access to evaluation strategies that go beyond traditional translation quality evaluation, enabling researchers and engineers to better understand the performance of a NMT model and also easily measure system's biases.