TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation
This provides a new benchmark for researchers to assess tense consistency in machine translation, addressing a specific linguistic issue in the field.
The authors tackled the problem of tense inconsistency in machine translation by creating a parallel tense test set with 552 French-English utterances and introducing a benchmark for tense prediction accuracy, enabling measurement of tense consistency performance.
Tense inconsistency frequently occurs in machine translation. However, there are few criteria to assess the model's mastery of tense prediction from a linguistic perspective. In this paper, we present a parallel tense test set, containing French-English 552 utterances. We also introduce a corresponding benchmark, tense prediction accuracy. With the tense test set and the benchmark, researchers are able to measure the tense consistency performance of machine translation systems for the first time.