How good are gpt models at machine translation? a comprehensive evaluation

A Hendy, M Abdelrehim, A Sharaf, V Raunak… - arXiv preprint arXiv …, 2023 - arxiv.org
… We also show that hybrid approaches, which combine GPT … 2022). There has also been a
series of recent works on in… shots along with the best WMT systems and MS-Translator. Table 3 …

A paradigm shift in machine translation: Boosting translation performance of large language models

H Xu, YJ Kim, A Sharaf, HH Awadalla - arXiv preprint arXiv:2309.11674, 2023 - arxiv.org
… test datasets from WMT’17 to WMT’20, plus the development and test sets from Flores-200
(NLLB TEAM et al., 2022), resulting in … In Proceedings of the Seventh Conference on Machine

Contrastive preference optimization: Pushing the boundaries of llm performance in machine translation

H Xu, A Sharaf, Y Chen, W Tan, L Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
2022). Given a set of source sentences x, alongside preferred … Lastly, we include comparisons
with the WMT competition winners… In Proceedings of the Seventh Conference on Machine

Findings of the WMT 2023 shared task on quality estimation

F Blain, C Zerva, R Rei, NM Guerreiro… - … Machine Translation, 2023 - aclanthology.org
… They then split the labelled data from the WMT 2022 QE task into 20 … Proceedings of the
Seventh Conference on Machine Translation (WMT), pages 69–99, Abu Dhabi, United Arab

Findings of the second WMT shared task on sign language translation (WMT-SLT23)

M Müller, M Alikhani, E Avramidis, R Bowden… - … on machine translation …, 2023 - hal.science
… 3 Tracks and submission procedure … Table 2: Comparison between SRF training data of
the 2022 and 2023 edition of the WMT-SLT shared task. Subtitle segmentation=ensuring that …

Linguistically Motivated Evaluation of the 2023 State-of-the-art Machine Translation: Can ChatGPT Outperform NMT?

S Manakhimova, E Avramidis… - … Machine Translation, 2023 - aclanthology.org
machine translation outputs in the context of the Shared Task at the 8th Conference of Machine
Translation (… 2022). Our approach enables a comprehensive analysis that spans over a …

ebleu: Unexpectedly good machine translation evaluation using simple word embeddings

M ElNokrashy, T Kocmi - … Conference on Machine Translation, 2023 - aclanthology.org
2022). The source segments and human reference … In Proceedings of the Seventh
Conference on Machine Translation (WMT), pages 46–68, Abu Dhabi, United Arab

Findings of the WMT 2023 Shared Task on Machine Translation with Terminologies

K Semenov, V Zouhar, T Kocmi, D Zhang… - … Machine Translation, 2023 - aclanthology.org
2022), this ranking is likely more close to the true quality. … In Proceedings of the Seventh
Conference on Machine Translation (WMT), Singapore, Singapore (Hybrid). Association for …

Findings of the WMT 2023 Shared Task on Automatic Post-Editing

P Bhattacharyya, R Chatterjee, M Freitag… - … Machine Translation, 2023 - aclanthology.org
… We presented the results from the 9th shared task on Automatic Post-Editing at WMT. In
continuity with the 2022 round, the task focused on the automatic correction of NMT outputs …

Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution

N Xu, J Zhao, C Zu, T Gui, Q Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
… use of RLHF to improve machine translation quality and propose a … 2022) to assess the
model’s performance. Note that WMT23 … In Proceedings of the Seventh Conference on Machine