Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices
This addresses methodological issues for researchers in natural language processing, but it is incremental as it synthesizes existing practices without introducing new metrics.
The paper surveyed current evaluation practices using automatic metrics in natural language generation, finding significant shortcomings such as inappropriate usage and lack of correlation with human judgments.
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.