Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation

Mengge Liu, Wen Zhang, Xiang Li, Jian Luan, Bin Wang, Yuhang Guo*, Shuoying Chen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. However, the general full-sentence translation test set is acquired by offline translation of the entire source sentence, which is not designed for SimulMT evaluation, making us rethink whether this will underestimate the performance of SimulMT models. In this paper, we manually annotate a monotonic test set based on the MuST-C English-Chinese test set, denoted as SiMuST-C. Our human evaluation confirms the acceptability of our annotated test set. Evaluations on three different SimulMT models verify that the underestimation problem can be alleviated on our test set. Further experiments show that finetuning on an automatically extracted monotonic training set improves SimulMT models by up to 3 BLEU points.

Original languageEnglish
Title of host publicationICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728163277
DOIs
Publication statusPublished - 2023
Event48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 202310 Jun 2023

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2023-June
ISSN (Print)1520-6149

Conference

Conference48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Country/TerritoryGreece
CityRhodes Island
Period4/06/2310/06/23

Keywords

  • Machine Translation
  • Simultaneous Machine Translation Evaluation

Fingerprint

Dive into the research topics of 'Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation'. Together they form a unique fingerprint.

Cite this