This paper presents KU X Upstage's submission to the quality estimation (QE): critical error detection (CED) shared task in WMT22. We leverage the XLM-RoBERTa large model without utilizing any additional parallel data. To the best of our knowledge, we apply prompt-based fine-tuning to the QE task for the first time. To maximize the model's language understanding capability, we reformulate the CED task to be similar to the masked language model objective, which is a pre-training strategy of the language model. We design intuitive templates and label words, and include auxiliary descriptions such as demonstration or Google Translate results in the input sequence. We further improve the performance through the template ensemble, and as a result of the shared task, our approach achieve the best performance for both English-German and Portuguese-English language pairs in an unconstrained setting.
|Title of host publication
|WMT 2022 - 7th Conference on Machine Translation, Proceedings of the Conference
|Association for Computational Linguistics
|Number of pages
|Published - 2022
|7th Conference on Machine Translation, WMT 2022 - Abu Dhabi, United Arab Emirates
Duration: 2022 Dec 7 → 2022 Dec 8
|Conference on Machine Translation - Proceedings
|7th Conference on Machine Translation, WMT 2022
|United Arab Emirates
|22/12/7 → 22/12/8
Bibliographical noteFunding Information:
This research was supported by the Ministry of Science and ICT (MSIT), Korea, under the Information Technology Research Center (ITRC) support program (IITP-2022-2018-0-01405) supervised by the Institute for Information & Communications Technology Planning & Evaluation(IITP) and this work was supported by an IITP grant funded by the MSIT (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques) and this research was supported by the MSIT, Korea, under the ICT Creative Consilience program (IITP-2022-2020-0-01819) supervised by the IITP.
© 2022 Association for Computational Linguistics.
ASJC Scopus subject areas
- Language and Linguistics
- Human-Computer Interaction