# The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT

arXiv: https://arxiv.org/abs/1605.04809 · HTML: https://mlsanity.com/paper/1605.04809/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2016.

## Built on by (most cited first, 6 of 6)

- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation](https://mlsanity.com/paper/2203.03910/) (2022)
- [Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition](https://mlsanity.com/paper/2210.15282/) (2022)
- [On-the-Fly Fusion of Large Language Models and Machine Translation](https://mlsanity.com/paper/2311.08306/) (2023)
- [PePe: Personalized Post-editing Model utilizing User-generated Post-edits](https://mlsanity.com/paper/2209.10139/) (2022)
- [Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies](https://mlsanity.com/paper/2408.11327/) (2024)

## Abstract (arXiv)

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared task on news translation. We explore methods of decode-time integration of attention-based neural translation models with phrase-based statistical machine translation. Efficient batch-algorithms for GPU-querying are proposed and implemented. For English-Russian, our system stays behind the state-of-the-art pure neural models in terms of BLEU. Among restricted systems, manual evaluation places it in the first cluster tied with the pure neural model. For the Russian-English task, our submission achieves the top BLEU result, outperforming the best pure neural system by 1.1 BLEU points and our own phrase-based baseline by 1.6 BLEU. After manual evaluation, this system is the best restricted system in its own cluster. In follow-up experiments we improve results by additional 0.8 BLEU.