Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices

P Schmidtová, S Mahamood, S Balloccu… - arXiv preprint arXiv …, 2024 - arxiv.org
arXiv preprint arXiv:2408.09169, 2024arxiv.org
Automatic metrics are extensively used to evaluate natural language processing systems.
However, there has been increasing focus on how they are used and reported by
practitioners within the field. In this paper, we have conducted a survey on the use of
automatic metrics, focusing particularly on natural language generation (NLG) tasks. We
inspect which metrics are used as well as why they are chosen and how their use is
reported. Our findings from this survey reveal significant shortcomings, including …
Automatic metrics are extensively used to evaluate natural language processing systems. However, there has been increasing focus on how they are used and reported by practitioners within the field. In this paper, we have conducted a survey on the use of automatic metrics, focusing particularly on natural language generation (NLG) tasks. We inspect which metrics are used as well as why they are chosen and how their use is reported. Our findings from this survey reveal significant shortcomings, including inappropriate metric usage, lack of implementation details and missing correlations with human judgements. We conclude with recommendations that we believe authors should follow to enable more rigour within the field.
arxiv.org
Showing the best result for this search. See all results