← Authors

Alon Lavie

35 papers · 2003–2026 · 7 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (31) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (22) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (15) πŸ”¬ Deep Specialist (12) 🀝 Dynamic Duo (12) 🧬 Topic Evolution πŸ”₯ Unstoppable (7) πŸ—ƒοΈ Keyword Collector (73) πŸ’Ž Century Club (34) ❓ The Questioner (2)

Conferences

EMNLP (16) ACL (9) NAACL (5) EACL (2) COLING (1) CONLL (1) IJCNLP (1)

Top co-authors

Ricardo Rei (12) Craig Stewart (9) Ana C Farinha (8) Chrysoula Zerva (6) Chi-kiu Lo (5) Markus Freitag (5) Chris Dyer (5) Luísa Coheur (5) Tom Kocmi (4) John Mendonça (4)

Keywords

machine translation (12) quality estimation (6) machine translation evaluation (4) translation evaluation (4) human evaluation (4) large language model (3) neural network (3) metric correlation (2) quality metric (2) quality assessment (2) conversational ai (2) automatic metric (2) automatic evaluation (2) neural metric (2) statistical significance (2) dialogue evaluation (2) ensemble learning (2) reference-free evaluation (2) evaluation metrics (2) segment-level analysis (2)

Papers

MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators EACL 2026
Findings of the WMT25 Shared Task on Automated Translation Evaluation Systems: Linguistic Diversity is Challenging and References Still Help EMNLP 2025
CUNI and Phrase at WMT25 MT Evaluation Task EMNLP 2025
On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation ACL 2024
Are LLMs Breaking MT Metrics? Results of the WMT24 Metrics Shared Task EMNLP 2024
Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs EMNLP 2024
Dialogue Quality and Emotion Annotations for Customer Support Conversations EMNLP 2023
The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics ACL 2023
Results of WMT23 Metrics Shared Task: Metrics Might Be Guilty but References Are Not Innocent EMNLP 2023
CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task EMNLP 2022
Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust EMNLP 2022
COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task EMNLP 2022
Results of the WMT21 Metrics Shared Task: Evaluating Metrics with Expert-based Human Evaluations on TED and News Domain EMNLP 2021
MT-Telescope: An interactive platform for contrastive evaluation of MT systems ACL 2021
Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task EMNLP 2021
MT-Telescope: An interactive platform for contrastive evaluation of MT systems IJCNLP 2021
Unbabel’s Participation in the WMT20 Metrics Shared Task EMNLP 2020
COMET: A Neural Framework for MT Evaluation EMNLP 2020
Synthesizing Compound Words for Machine Translation ACL 2016
Humor Recognition and Humor Anchor Extraction EMNLP 2015
Learning from Post-Editing: Online Model Adaptation for Statistical Machine Translation EACL 2014
Improving Syntax-Augmented Machine Translation by Coarsening the Label Set NAACL 2013
Grouping Language Model Boundary Words to Speed K–Best Extraction from Hypergraphs NAACL 2013
Language Model Rest Costs and Space-Efficient Storage EMNLP 2012
Language Model Rest Costs and Space-Efficient Storage CONLL 2012
Unsupervised Word Alignment with Arbitrary Features ACL 2011
Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability ACL 2011
Extending the METEOR Machine Translation Evaluation Metric to the Phrase Level NAACL 2010
A Best-First Probabilistic Shift-Reduce Parser ACL 2006
Parser Combination by Reparsing NAACL 2006
A Best-First Probabilistic Shift-Reduce Parser COLING 2006
Multi-Engine Machine Translation Guided by Explicit Word Matching ACL 2005
Automatic Measurement of Syntactic Development in Child Language ACL 2005
BLANC: Learning Evaluation Metrics for MT EMNLP 2005
Speechalator: Two-Way Speech-to-Speech Translation in Your Hand NAACL 2003