Alon Lavie
Research Subjects
Alon Lavie has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Craig Stewart2 shared publications
- Ricardo Rei
Unbabel
2 shared publications - Ana C Farinha1 shared publication
Catarina Farinha
1 shared publicationIsabel Trancoso
INESC-ID Lisbon
1 shared publicationJohn Mendonca
INESC-ID Lisbon
1 shared publication
Latest Publications
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 83-90
QualityAdapt: an Automatic Dialogue Quality Estimation Framework
John Mendonca, Alon Lavie, Isabel Trancoso. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 83-90
Open AccessQualityAdapt: an Automatic Dialogue Quality Estimation Framework
John Mendonca, Alon Lavie, Isabel Trancoso. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.
- Open Access
Unbabel's Participation in the WMT20 Metrics Shared Task
We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segment-level, document-level and system-level tracks on all language pairs, as well as the 'QE as a Metric' track. Accordingly, we illustrate results of our models in these tracks with reference to test sets from the previous year. Our submissions build upon the recently proposed COMET framework: We train several estimator models to regress on different human-generated quality scores and a novel ranking model trained on relative ranks obtained from Direct Assessments. We also propose a simple technique for converting segment-level predictions into a document-level score. Overall, our systems achieve strong results for all language pairs on previous test sets and in many cases set a new state-of-the-art.
Open AccessUnbabel's Participation in the WMT20 Metrics Shared Task
We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segment-level, document-level and system-level tracks on all language pairs, as well as the 'QE as a Metric' track. Accordingly, we illustrate results of our models in these tracks with reference to test sets from the previous year. Our submissions build upon the recently proposed COMET framework: We train several estimator models to regress on different human-generated quality scores and a novel ranking model trained on relative ranks obtained from Direct Assessments. We also propose a simple technique for converting segment-level predictions into a document-level score. Overall, our systems achieve strong results for all language pairs on previous test sets and in many cases set a new state-of-the-art.
- Open Access
COMET: A Neural Framework for MT Evaluation
We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in cross-lingual pretrained language modeling resulting in highly multilingual and adaptable MT evaluation models that exploit information from both the source input and a target-language reference translation in order to more accurately predict MT quality. To showcase our framework, we train three models with different types of human judgements: Direct Assessments, Human-mediated Translation Edit Rate and Multidimensional Quality Metrics. Our models achieve new state-of-the-art performance on the WMT 2019 Metrics shared task and demonstrate robustness to high-performing systems.
Open AccessCOMET: A Neural Framework for MT Evaluation
We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in cross-lingual pretrained language modeling resulting in highly multilingual and adaptable MT evaluation models that exploit information from both the source input and a target-language reference translation in order to more accurately predict MT quality. To showcase our framework, we train three models with different types of human judgements: Direct Assessments, Human-mediated Translation Edit Rate and Multidimensional Quality Metrics. Our models achieve new state-of-the-art performance on the WMT 2019 Metrics shared task and demonstrate robustness to high-performing systems.