Multilingual Representations for NLP

Multilingual 2021


Artificial Intelligence





Special Issue on "Multilingual Representations for NLP"
*Aims and Scope*
This special issue invites articles on all aspects of multi- and cross-lingual text representations inNLP. Beyond standard zero-shot cross-lingual text classification transfer, particular focus is onchallenging application scenarios of cross-lingual representations such as using them as a basisfor evaluation metrics in machine translation without human references (reference-free evaluationmetrics) and scenarios involving (very) low-resource languages and highly distant language pairs.Analyses of cross-lingual representations and novel benchmarks are, furthermore, of high interest.Further main topics are listed below.
Original submissions as well as substantial extensions of submitted conference papers arewelcome.
*Main Topics*
-Evaluation metrics for MT based on cross-lingual representations (“reference-free evaluation”)
-Evaluation of cross-lingual representations for low-resource languages and highly distant language pairs
-Explainability and interpretability of multi- and cross-lingual representations
-Novel analyses of cross-lingual and multilingual representations
-Measuring language similarity from cross-lingual representations
-Predicting missing typological features from multilingual representations
-Extending representations to new languages and tasks with minimal supervision
-Self-supervised cross-lingual representation learning
-Zero-shot or few-shot cross-lingual transfer for language understanding and generation
-Automatic large-scale multilingual corpus mining
-Cost-effective annotation for multilingual applications
-Resources for training or evaluating cross-lingual representations
-Novel cross-lingual and multilingual benchmarks
*How to Submit*
Please visit journal author guideline at: https://www.atlantis-press.com/journals/nlpr/author-guidelines
more information please contact Yanhua.li@atlantis-press.com