Multilingual NLP
An exciting research direction that we pursue at GMU NLP is building multi-lingual and polyglot systems. The languages of the world often share similar characteristics, and training systems cross-lingually allows us to leverage these similarities and overcome data scarcity issues.
George Mason NLP
The Natural Language Processing group at George Mason University. We work on multilingual models, on and on building robust NLP systems, especially for low-resource and endangered languages.
Related
- Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis
- Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing
- Unlearning Climate Misinformation in Large Language Models
- Script-Agnostic Language Identification
- A Study on Scaling Up Multilingual News Framing Analysis
Posts
Predicting Performance for Natural Language Processing Tasks
This is a post regarding our paper that will be presented at ACL 2020. tl;dr: You can use previously published results to get an estimation of the performance on a new experiment, before running it! We describe NLP experiments with a set of interpretable features, and train prediction models which are actually pretty good at producing such estimations, and show how they can be useful in various scenarios.
Should All Cross-Lingual Embeddings Speak English?
This is a post regarding our paper that got accepted at ACL 2020.
Word embeddings are ubiquitous in modern NLP, from static ones (like word2vec or fasttext) to contextual representations obtained from ELMo, BERT, and other models. One very interesting property of learned word embeddings is that, since they (ideally) model the syntactic or semantic relations between words, the embedding space that we learn in two different languages will have somewhat similar properties and structure.
A note on evaluating multilingual benchmarks
A note on evaluating multilingual benchmarks
Antonis Anastasopoulos, December 2019.
tl;dr: Be careful when reporting averages for multilingual benchmarks, especially if making claims about multilinguality. In addition, averaging by language family can provide additional insights.