Cued@wmt19:ewc&lms
Not on the map. Why?
Abstract (arXiv)
Two techniques provide the fabric of the Cambridge University Engineering Department's (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). We report substantial gains by fine-tuning very strong baselines on former WMT test sets using a combination of checkpoint averaging and EWC. A sentence-level Transformer LM and a document-level LM based on a modified Transformer architecture yield further gains. As in previous years, we also extract n-gram probabilities from SMT lattices which can be seen as a source-conditioned n-gram LM.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 1.
5 papers.
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
- 2022Revisiting Checkpoint Averaging for Neural Machine Translationcited by 13
- 2023Document-Level Language Models for Machine Translationcited by 12
- 2022Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognitioncited by 10
- 2024Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabulariescited by 0
- 2024Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies21 Aug 2024
- 2023Document-Level Language Models for Machine Translation18 Oct 2023
- 2022Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition27 Oct 2022
- 2022Revisiting Checkpoint Averaging for Neural Machine Translation21 Oct 2022
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey14 Apr 2021