Abstract
This paper describes our submission to the WMT2022 shared metrics task. Our unsupervised metric estimates the translation quality at chunk-level and sentence-level. Source and target sentence chunks are retrieved by using a multi-lingual chunker. The chunk-level similarity is computed by leveraging BERT contextual word embeddings and sentence similarity scores are calculated by leveraging sentence embeddings of Language-Agnostic BERT models. The final quality estimation score is obtained by mean pooling the chunk-level and sentence-level similarity scores. This paper outlines our experiments and also reports the correlation with human judgements for en-de, en-ru and zh-en language pairs of WMT17, WMT18 and WMT19 test sets.- Anthology ID:
- 2022.wmt-1.50
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 564–568
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.50
- DOI:
- Cite (ACL):
- Ananya Mukherjee and Manish Shrivastava. 2022. REUSE: REference-free UnSupervised Quality Estimation Metric. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 564–568, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- REUSE: REference-free UnSupervised Quality Estimation Metric (Mukherjee & Shrivastava, WMT 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.50.pdf