# QCRI Machine Translation Systems for IWSLT 16

arXiv: https://arxiv.org/abs/1701.03924 · HTML: https://mlsanity.com/paper/1701.03924/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2017.

## Built on by (most cited first, 3 of 3)

- [AraT5: Text-to-Text Transformers for Arabic Language Generation](https://mlsanity.com/paper/2109.12068/) (2021)
- [TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties](https://mlsanity.com/paper/2308.03051/) (2023)
- [TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation](https://mlsanity.com/paper/2206.03933/) (2022)

## Abstract (arXiv)

This paper describes QCRI's machine translation systems for the IWSLT 2016 evaluation campaign. We participated in the Arabic->English and English->Arabic tracks. We built both Phrase-based and Neural machine translation models, in an effort to probe whether the newly emerged NMT framework surpasses the traditional phrase-based systems in Arabic-English language pairs. We trained a very strong phrase-based system including, a big language model, the Operation Sequence Model, Neural Network Joint Model and Class-based models along with different domain adaptation techniques such as MML filtering, mixture modeling and using fine tuning over NNJM model. However, a Neural MT system, trained by stacking data from different genres through fine-tuning, and applying ensemble over 8 models, beat our very strong phrase-based system by a significant 2 BLEU points margin in Arabic->English direction. We did not obtain similar gains in the other direction but were still able to outperform the phrase-based system. We also applied system combination on phrase-based and NMT outputs.