📰 WMT 2023 — accepted papers

WMT 2023 is the 2023 edition of the Conference on Machine Translation (WMT), held in Singapore, December 2023 (publisher: Association for Computational Linguistics). The ACL Anthology lists 100 papers of it; our library holds 11 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

📍 Singapore · 🗓 December 2023

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. Findings of the WMT 2023 Shared Task on Quality EstimationFrederic Blain, Chrysoula Zerva, Ricardo Rei et al.73 citations · our summary
2. Large Language Models Effectively Leverage Document-level Context for Literary Translation, but Critical Errors PersistMarzena Karpinska, Mohit Iyyer65 citations · our summary
3. ChatGPT MT: Competitive for High- (but Not Low-) Resource LanguagesNathaniel Robinson, Perez Ogayo, David R. Mortensen et al.51 citations · our summary
4. Machine Translation with Large Language Models: Prompting, Few-shot Learning, and Fine-tuning with QLoRA ↗Xuan Zhang, Navid Rajabi, Kevin Duh et al.42 citations
5. Findings of the 2023 Conference on Machine Translation (WMT23): LLMs Are Here but Not Quite There Yet ↗Tom Kocmi, Eleftherios Avramidis, Rachel Bawden et al.38 citations
6. GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4Tom Kocmi, Christian Federmann36 citations · our summary
7. The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation EvaluationPatrick Fernandes, Daniel Deutsch, Mara Finkelstein et al.33 citations · our summary
8. Exploring Prompt Engineering with GPT Language Models for Document-Level Machine Translation: Insights and Findings ↗Yangjian Wu, Gang Hu28 citations
9. Domain Terminology Integration into Machine Translation: Leveraging Large Language Models ↗Yasmin Moslem, Gianfranco Romani, Mahdi Molaei et al.25 citations
10. Linguistically Motivated Evaluation of the 2023 State-of-the-art Machine Translation: Can ChatGPT Outperform NMT? ↗Shushen Manakhimova, Eleftherios Avramidis, Vivien Macketanz et al.20 citations

All accepted papers (100)

The most cited first; 11 with our summary link to their page here, the others to the original.

1. Findings of the WMT 2023 Shared Task on Quality EstimationFrederic Blain, Chrysoula Zerva, Ricardo Rei et al.73 citations · our summary
2. Large Language Models Effectively Leverage Document-level Context for Literary Translation, but Critical Errors PersistMarzena Karpinska, Mohit Iyyer65 citations · our summary
3. ChatGPT MT: Competitive for High- (but Not Low-) Resource LanguagesNathaniel Robinson, Perez Ogayo, David R. Mortensen et al.51 citations · our summary
4. Machine Translation with Large Language Models: Prompting, Few-shot Learning, and Fine-tuning with QLoRA ↗Xuan Zhang, Navid Rajabi, Kevin Duh et al.42 citations
5. Findings of the 2023 Conference on Machine Translation (WMT23): LLMs Are Here but Not Quite There Yet ↗Tom Kocmi, Eleftherios Avramidis, Rachel Bawden et al.38 citations
6. GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4Tom Kocmi, Christian Federmann36 citations · our summary
7. The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation EvaluationPatrick Fernandes, Daniel Deutsch, Mara Finkelstein et al.33 citations · our summary
8. Exploring Prompt Engineering with GPT Language Models for Document-Level Machine Translation: Insights and Findings ↗Yangjian Wu, Gang Hu28 citations
9. Domain Terminology Integration into Machine Translation: Leveraging Large Language Models ↗Yasmin Moslem, Gianfranco Romani, Mahdi Molaei et al.25 citations
10. Linguistically Motivated Evaluation of the 2023 State-of-the-art Machine Translation: Can ChatGPT Outperform NMT? ↗Shushen Manakhimova, Eleftherios Avramidis, Vivien Macketanz et al.20 citations
11. Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared TaskRicardo Rei, Nuno M. Guerreiro, José Pombal et al.20 citations · our summary
12. Findings of the WMT 2023 Shared Task on Automatic Post-Editing ↗Pushpak Bhattacharyya, Rajen Chatterjee, Markus Freitag et al.17 citations
13. Results of WMT23 Metrics Shared Task: Metrics Might Be Guilty but References Are Not InnocentMarkus Freitag, Nitika Mathur, Chi-kiu Lo et al.17 citations · our summary
14. Findings of the Second WMT Shared Task on Sign Language Translation (WMT-SLT23)Mathias Müller, Malihe Alikhani, Eleftherios Avramidis et al.16 citations · our summary
15. Towards Effective Disambiguation for Machine Translation with Large Language ModelsVivek Iyer, Pinzhen Chen, Alexandra Birch13 citations · our summary
16. Findings of the WMT 2023 Shared Task on Low-Resource Indic Language TranslationSantanu Pal, Partha Pakray, Sahinur Rahman Laskar et al.11 citations · our summary
17. HW-TSC's Participation in the WMT 2023 Automatic Post Editing Shared Task ↗Jiawei Yu, Min Zhang, Zhao Yanqing et al.11 citations
18. One Wide Feedforward Is All You Need ↗Telmo Pires, António Vilarinho Lopes, Yannick Assogba et al.11 citations
19. MetricX-23: The Google Submission to the WMT 2023 Metrics Shared TaskJuraj Juraska, Mara Finkelstein, Daniel Deutsch et al.8 citations · our summary
20. Cometoid: Distilling Strong Reference-based Machine Translation Metrics into Even Stronger Quality Estimation Metrics ↗Thamme Gowda, Tom Kocmi, Marcin Junczys-Dowmunt7 citations
21. Findings of the Word-Level AutoCompletion Shared Task in WMT 2023 ↗Lemao Liu, Francisco Casacuberta, George Foster et al.7 citations
22. Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting ↗Nikolay Bogoychev, Pinzhen Chen7 citations
23. Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level ↗Daniel Deutsch, Juraj Juraska, Mara Finkelstein et al.7 citations
24. Embed_Llama: Using LLM Embeddings for the Metrics Shared Task ↗Sören Dreano, Derek Molloy, Noel Murphy6 citations
25. Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs ↗Longyue Wang, Zhaopeng Tu, Yan Gu et al.6 citations

See all 100 papers in WMT 2023 — accepted papers →

📄 Papers with our summary in our library (11)

The most cited first (OpenAlex citations plus our library's).

1. GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4Conference on Machine Translation (WMT)Tom Kocmi, Christian Federmann2023 · 191 citations
2. The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation EvaluationConference on Machine Translation (WMT)Patrick Fernandes, Daniel Deutsch, Mara Finkelstein, et al.2023 · 156 citations
3. Large Language Models Effectively Leverage Document-level Context for Literary Translation, but Critical Errors PersistConference on Machine Translation (WMT)Marzena Karpinska, Mohit Iyyer2023 · 156 citations
4. Results of WMT23 Metrics Shared Task: Metrics Might Be Guilty but References Are Not InnocentConference on Machine Translation (WMT)Markus Freitag, Nitika Mathur, Chi-kiu Lo, et al.2023 · 155 citations
5. ChatGPT MT: Competitive for High- (but Not Low-) Resource LanguagesConference on Machine Translation (WMT)Nathaniel Robinson, Perez Ogayo, David R. Mortensen, et al.2023 · 151 citations
6. Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared TaskConference on Machine Translation (WMT)Ricardo Rei, Nuno M. Guerreiro, José Pombal, et al.2023 · 135 citations
7. Findings of the WMT 2023 Shared Task on Quality EstimationConference on Machine Translation (WMT)Frederic Blain, Chrysoula Zerva, Ricardo Rei, et al.2023 · 129 citations
8. MetricX-23: The Google Submission to the WMT 2023 Metrics Shared TaskConference on Machine Translation (WMT)Juraj Juraska, Mara Finkelstein, Daniel Deutsch, et al.2023 · 118 citations
9. Findings of the WMT 2023 Shared Task on Low-Resource Indic Language TranslationConference on Machine Translation (WMT)Santanu Pal, Partha Pakray, Sahinur Rahman Laskar, et al.2023 · 41 citations
10. Findings of the Second WMT Shared Task on Sign Language Translation (WMT-SLT23)Conference on Machine Translation (WMT)Mathias Müller, Malihe Alikhani, Eleftherios Avramidis, et al.2023 · 39 citations
11. Towards Effective Disambiguation for Machine Translation with Large Language ModelsConference on Machine Translation (WMT)Vivek Iyer, Pinzhen Chen, Alexandra Birch2023 · 38 citations

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🔁Machine translation (10)📏Evaluation & benchmarks (8)🌱Low-resource languages (2)

📚 Fields

🎭Arts and Humanities (11)🖥️Computer Science (11)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🎓Instituto Superior TécnicoLisbon · Portugal4 works here🎓Tilburg UniversityTilburg · Netherlands3 works here🔬Instituto de TelecomunicaçõesLisbon · Portugal3 works here🔬Instituto de Engenharia de Sistemas e Computadores Investigação e DesenvolvimentoLisbon · Portugal2 works here🏢MicrosoftRedmond · United States2 works here🎓Université Paris-SaclayGif-sur-Yvette · France2 works here🎓University of SurreyGuildford · United Kingdom2 works here🔬German Research Centre for Artificial IntelligenceKaiserslautern · Germany2 works here🎓Carnegie Mellon UniversityPittsburgh · United States2 works here🎓Northeastern UniversityBoston · United States1 work here🏢GoogleMountain View · United States1 work here🏢AmazonSeattle · United States1 work here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/wmt/2023/