George Mason NLP

George Mason NLP

George Mason University

George Mason Natural Language Processing Group

Natural language processing (NLP) aims to enable computers to use human languages – so that people can, for example, interact with computers naturally; or communicate with people who don’t speak a common language; or manipulate speech or text data at scales not otherwise possible. The NLP group at George Mason Computer Science is interested in all aspects of NLP, with a focus on building tools for under-served languages.

We are currently working on multilingual models, on building Machine Translation robust to L2-language variations, and on NLP for documentation of endangered languages.

News

  • March 2021 - 2 papers accepted at AfricaNLP! One is Claytone Sikasote and Antonis' paper on building a speech dataset for Bemba, the second is the internship work by Kathleen Siminyu on fine-tuning Speech Recognition models for Luhya languages. The papers are available on arXiv, along with a third pre-print on measuring syntactic well-formedness of text!
  • March 2021 - 1 paper accepted at NAACL! Preprint and details here .
  • January 2021 - Very excited to have received a grant from the National Endowment for the Humanities to build Optical Charachter Recognition tools for under-served languages (and especially Indigenous Latin American ones)!
  • January 2021 - Antonis spoke to the Global Podcast for the TICO-19 project.
  • November 2020 - Congratulations to Mahfuz for winning one of the two best paper awards at the W-NUT workshop!
  • December 2020 - Antonis will present a tutorial on NLP for endangered languages at COLING 2020 with Hilaria Cruz, Chistopher Cox, and Graham Neubig.
  • September 2020 - 4 papers accepted at the main EMNLP conference and 1 paper accepted at the Findings of EMNLP! Preprints are available below!
  • August 2020 - Antonis starting the NLP group at the George Mason Computer Science department!

Courses

Projects

Our research is/has been supported by the following organizations/companies:

NSF logo NEH logo Google logo Amazon logo
*

Speech

Most languages of the world are “oral”: they are not traditionally written and even if an alphabet exists, the community doesn’t usually use it. Hence, building NLP systems that can directly operate on speech input is paramount.

Morphology

Human language is marked by considerable diversity around the world, and the surface form of languages varies substantially. Morphology describes the way through which different word forms arise from lexemes. Computational morphology attempts to reproduce this process across languages, or uses machine learning models to model/discover the morphophonological processes that exist in a language.

Robustness

NLP systems are typically trained and evaluated in “clean” settings, over data without significant noise. However, systems deployed in the real world need to deal with vast amounts of noise. At GMU NLP we work towards making NLP systems more robust to several types of noise (adversarial or naturally occuring).

Language Documentation

Language Documentation aims at producing a permanent record that describes a language as used by its language community by producing a formal grammatical description along with a lexicon. Our group works on integrating NLP systems into the documentation workflow, aiming to speed-up the process and help the work of field linguists and language communities.

Machine Translation

Machine Translation is the task of translating between human languages using computers. Starting from simple word-for-word rule-based system in 1950s, we now have large multilingual neural models that can learn translate between dozens of languages.

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.

Members

Members

Avatar

Antonios Anastasopoulos

Assistant Professor

Computational Linguistics, Machine Translation, Speech Recognition, NLP for Endangered Languages

Avatar

Md Mahfuz Ibn Alam

PhD Student

Natural Language Processing, Machine Learning, Computer Vision, Common Sense Reasoning

Avatar

Fahim Faisal

PhD Student

Computational linguistics, Natural language processing, Machine learning

Avatar

Huayu Zhou

PhD Student

Natural Language Processing, Machine Translation, Machine Learning, Data Mining

Avatar

Ruoyu (Roy) Xie

Undergraduate Student

Natural Language Processing, Machine Learning, Computer Vision

Avatar

Sharlina Keshava

CS Master’s Student

Natural Language Processing, Fairness in AI, Multilingual NLP, Machine Learning, Deep Learning

Vishwajeet Vijay Paradkar

Masters Student

Natural Language Processing

Collaborators

Claytone Sikasote

MS@African Masters of Machine Intelligence and Lecturer@University of Zambia

Language Processing for Bemba

Recent Publications

Browse all publications.

Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties. arXiv, 2021.

PDF Project

Evaluating the Morphosyntactic Well-formedness of Generated Texts. arXiv, 2021.

PDF Code

Reducing Confusion in Active Learning for Part-Of-Speech Tagging. Transactions of the Association for Computational Linguistics (TACL), 2021.

PDF Code

Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations. International Conference on Computational Linguistics (COLING), 2020.

PDF Code Slides Video

X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020.

PDF Code Dataset