Murhaf Fares

Email: [first name + first letter of last name]@ifi.uio.no

PhD fellow at the Language Technology Group (Department of Informatics, University of Oslo) working on ML approaches for noun-noun compound analysis.

Education

PhD FellowUniversity of Oslo, December 2014 -

Language Technology Group

MSc Language and CommunicationUniversity of Oslo, 2011 - 2013

An interdisciplinary, research-oriented two-year Master of Science degree at the interface of Computer Science and Linguistics.

Bachelor of EngineeringDamascus University, 2006 - 2011

Publications
Murhaf Fares Stephan Oepen and Erik Velldal. Transfer and Multi-Task Learning for Noun–Noun Compound Interpretation. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). [PDF]

Murhaf Fares, Stephan Oepen, Lilja Øvrelid, Jari Björne and Richard Johansson. The 2018 Shared Task on Extrinsic Parser Evaluation: On the Downstream Utility of English Universal Dependency Parsers. Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. [PDF]

Murhaf Fares, Andrey Kutuzov, Stephan Oepen and Erik Velldal. Word vectors, reuse, and replicability: Towards a community repository of large-text resources. Proceedings of the 21st Nordic Conference on Computational Linguistics [PDF]

Murhaf Fares. A Dataset for Joint Noun–Noun Compound Bracketing and Interpretation. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop. [PDF]

Murhaf Fares, Stephan Oepen and Erik Velldal. Identifying Compounds: On The Role of Syntax. Proceedings of the Fourteenth Workshop on Treebanks and Linguistic Theories (TLT14). [PDF]

Murhaf Fares, Stephan Oepen and Yi Zhang. Machine Learning for High-Quality Tokenization Replicating Variable Tokenization Schemes. In International Conference on Intelligent Text Processing and Computational Linguistics (pp. 231-244). Springer Berlin Heidelberg. [Link]

Murhaf Fares. ERG Tokenization and Lexical Categorization: A sequence labeling approach. Master's Thesis - University of Oslo. [PDF]
Teaching
Autumn 2016: INF4820 Algorithms for Artificial Intelligence and Natural Language Processing
Autumn 2017: INF4820 Algorithms for Artificial Intelligence and Natural Language Processing