Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task
Year: 2021
Type: other
Abstract: In this paper, we present the joint contribution of Unbabel and IST to the WMT 2021 Metrics Shared Task. With this year's focus on Multidimensional Quality Metric (MQM) as the ground-truth human assessment, our aim was to steer COMET towards higher correlations with MQM. We do so by first pre-training on Direct Assessments and then fine-tuning on z-normalized MQM scores. In our experiments we also show that reference-free COMET models are becoming competitive with reference-based models, even outperforming the best COMET model from 2020 on this year's development data. Additionally, we present COMETinho, a lightweight COMET model that is 19x faster on CPU than the original model, while also achieving state-of-the-art correlations with MQM. Finally, in the "QE as a metric'' track, we also participated with a QE model trained using the OpenKiwi framework leveraging MQM scores and word-level annotations.
Source: Underline Science Inc.
DOI: 10.48448/wrjt-a678
Authors: Association for Computational Linguistics 2021, Farinha, Ana C, Lavie, Alon, Martins, André, Ramos, Pedro, Rei, Ricardo, Stewart, Craig, Taisiya Glushkova, Taisiya Glushkova, van Stigt, Daan, Zerva, Chrysoula
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6910414005
Cites:
Cited by:
Related to: