Marjan Ghazvininejad
RESEARCH SCIENTIST | SEATTLE, UNITED STATES
Marjan is a Research Scientist at Facebook AI Research. Marjan received her Ph.D. at the University of Southern California on neural creative language generation. She is interested in text representation, language generation, and machine translation. Marjan's recent focus has been on new approaches for modeling and training of these systems to generate high quality, coherent, and creative text.
Research Areas
Marjan's Work
Marjan's Publications
October 27, 2023
CONVERSATIONAL AI
NLP
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa
October 27, 2023
December 06, 2020
RESEARCH
NLP
Pre-training via Paraphrasing
Michael Lewis, Armen Aghajanyan, Gargi Ghosh, Luke Zettlemoyer, Marjan Ghazvininejad, Sida Wang
December 06, 2020
July 15, 2020
RESEARCH
ML APPLICATIONS
Aligned Cross Entropy for Non-Autoregressive Machine Translation
Marjan Ghazvininejad, Luke Zettlemoyer, Omer Levy, Vladimir Karpukhin
July 15, 2020
July 15, 2020
Non-autoregressive Translation with Disentangled
Marjan Ghazvininejad, James Cross, Jiatao Gu, Jungo Kasai
July 15, 2020
July 06, 2020
RESEARCH
NLP
Simple and Effective Retrieve-Edit-Rerank Text Generation
Marjan Ghazvininejad, Luke Zettlemoyer, Nabil Hossain
July 06, 2020
June 30, 2020
RESEARCH
NLP
Non-Autoregressive Machine Translation with Disentangled Context Transformer
Jungo Kasai, James Cross, Jiatao Gu, Marjan Ghazvininejad
June 30, 2020
November 02, 2019
RESEARCH
NLP
Mask-Predict: Parallel Decoding of Conditional Masked Language Models
Marjan Ghazvininejad, Luke Zettlemoyer, Omer Levy, Yinhan Liu
November 02, 2019
July 25, 2019
RESEARCH
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
Marjan Ghazvininejad, Jonathan May, Kevin Knight, Nada Aldarrab, Nima Pourdamghani
July 25, 2019
Product experiences
Foundational models
Product experiences
Latest news
Foundational models
Meta © 2024