CUNI Submission in WMT22 General Task
Not on the map. Why?
Abstract (arXiv)
We present the CUNI-Bergamot submission for the WMT22 General translation task. We compete in EnglishrightarrowCzech direction. Our submission further explores block backtranslation techniques. Compared to the previous work, we measure performance in terms of COMET score and named entities translation accuracy. We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show a possible synergy when using both of the techniques simultaneously. The results show that both approaches are effective means of improving translation quality and they yield even better results when combined.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 29 Nov 2022.
Builds on
14 of 27 references.
References · 14
- 2017Attention Is All You Needcited by 60,361
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
- 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
- 2018Marian: Fast Neural Machine Translation in C++cited by 203
- 2020If beam search is the answer, what was the question?cited by 116
- 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
- 2019Improving Deep Transformer with Depth-Scaled Initialization and Merged Attentioncited by 59
- 2019Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translationcited by 56
- 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
- 2022Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMETcited by 41
2 more
- 2020Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawordscited by 17
- 2019Neural Generation for Czech: Data and Baselinescited by 13
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.