Alireza Mohammadshahi
Biography
I’m a Ph.D. student of the EDIC department at EPFL, and research assistant at IDIAP research institute. I’m a member of the Natural Language Understanding group under the supervision of Dr. James Henderson. I received my bachelor’s degree in electrical engineering from Sharif University of Technology (also minor in computer science). I’m currently working on applying deep learning models on natural languages, specifically representation learning, and structure prediction, and machine translation. During my Ph.D., I was Research Intern of NAVERLABS Europe and Meta AI.Publications
Selected publications
Alireza Mohammadshahi, James Henderson Arxiv |
Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling |
Alireza Mohammadshahi, James Henderson Transactions of the Association for Computational Linguistics, February 2021 |
Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement |
Mohammadshahi Alireza, Henderson James 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings, November 2020 |
Graph-to-Graph Transformer for Transition-based Dependency Parsing |
Alireza Mohammadshahi, Rémi Lebret, Karl Aberer Association for Computational Linguistics, November 2019 |
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task |
James Barry, Alireza Mohammadshahi, Joachim Wagner, Jennifer Foster, James Henderson ACL-IWPT , August 2021 |
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task |
Luis Espinosa-Anke, Alexander Shvets, Alireza Mohammadshahi, James Henderson, Leo Wanner The 11th Joint Conference on Lexical and Computational Semantics (*SEM 2022) , May 2022 |
Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers |
Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard, Caroline Brun, James Henderson, Laurent Besacier The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) , October 2022 |
What Do Compressed Multilingual Machine Translation Models Forget? |
Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard, Caroline Brun, James Henderson, Laurent Besacier The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) , October 2022 |
SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages |