The SPECTRANS System Description for the WMT21 Terminology Task - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

The SPECTRANS System Description for the WMT21 Terminology Task

Dahn Cho
  • Function : Author
Zong-You Ke
  • Function : Author
  • PersonId : 1126038
Lichao Zhu

Abstract

This paper discusses the WMT 2021 terminology shared task from a "meta" perspective. We present the results of our experiments using the terminology dataset and the OpenNMT (Klein et al., 2017) and JoeyNMT (Kreutzer et al., 2019) toolkits for the language direction English to French. Our experiment 1 compares the predictions of the two toolkits. Experiment 2 uses OpenNMT to fine-tune the model. We report our results for the task with the evaluation script but mostly discuss the linguistic properties of the terminology dataset provided for the task. We provide evidence of the importance of text genres across scores, having replicated the evaluation scripts.

Domains

Linguistics
Fichier principal
Vignette du fichier
WMT2021_Shared_task_EMNLP2021_SPECTRANS_submission (1).pdf (354.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03574680 , version 1 (15-02-2022)

Identifiers

  • HAL Id : hal-03574680 , version 1

Cite

Nicolas Ballier, Dahn Cho, Bilal Faye, Zong-You Ke, Hanna Martikainen, et al.. The SPECTRANS System Description for the WMT21 Terminology Task. EMNLP 2021 SIXTH CONFERENCE ON MACHINE TRANSLATION (WMT21), ACL, Nov 2021, Punta Cana, Dominican Republic. pp.815-820. ⟨hal-03574680⟩
142 View
79 Download

Share

Gmail Facebook X LinkedIn More