Ali Basirat

Universal Dependency Parsing

In this project, we extend existing dependency-based parsing models to better cope typological diversity and adapt them to the representations of Universal Dependencies.

  1. Ali Basirat and Joakim Nivre, Syntactic Nuclei in Dependency Parsing -- A Multilingual Exploration, To be presented at the 16th conference of the European Chapter of the Association for Computational Linguistics (EACL-2021) (2021) [code]

  2. Ali Basirat, Miryam de Lhoneux, Artur Kulmizev, Murathan Kurfali, Joakim Nivre and Robert Östling, Polyglot Parsing for One Thousand and One Languages (And Then Some), First workshop on Typology for Polyglot NLP (2019)

  3. Miryam de Lhoneux, Yan Shao, Ali Basirat, Eliyahu Kiperwasser, Sara Stymne, Yoav Goldberg, and Joakim Nivre, From Raw Text to Universal Dependencies - Look, No Tags!, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2017)

Word Embeddings and Dependency Parsing
  1. Ali Basirat, Extraction of Word-vectors from Supertag Distribution for Dependency Parsing (2016)

  2. Ali Basirat, Transition-based Dependency Parsing with Continuous Word Vectors (2015)

  3. Ali Basirat, and Joakim Nivre, Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features (2015)