My interests are centered around syntax and parsing. I like to work on syntactic parsing because it allows exploring interesting linguistic phenomena while working on a system that is central to NLP and useful to many applications. I am particularly interested in work on syntax and parsing in a multilingual perspective. In general, I like work that is at the intersection between linguistics and NLP/Machine Learning.
For my PhD, I am working on parsing with Universal Dependencies.
- Miryam de Lhoneux, Johannes Bjerva, Isabelle Augenstein and Anders Søgaard. 2018. Parameter sharing between dependency parsers for related languages. To appear at EMNLP. [pdf|code]
- Aaron Smith, Miryam de Lhoneux, Sara Stymne and Joakim Nivre. 2018. An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing. To appear at EMNLP. [pdf]
- Anders Søgaard, Miryam de Lhoneux and Isabelle Augenstein. 2018. Nightmare at test time: How punctuation prevents parsers from generalizing. To appear at the BlackboxNLP workshop. [pdf]
- Aaron Smith, Bernd Bohnet, Miryam de Lhoneux, Joakim Nivre, Yan Shao and Sara Stymne. 2018. 82 Treebanks, 34 Models: Universal Dependency Parsing with Cross-Treebank Models. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies.
- Sara Stymne, Miryam de Lhoneux, Aaron Smith and Joakim Nivre. 2018. Parser Training with Heterogeneous Treebanks. ACL [pdf]
- Miryam de Lhoneux, Sara Stymne and Joakim Nivre. 2017. Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle. In Proceedings of the 15th International Conference on Parsing Technologies, pages 99-104, Association for Computational Linguistics. [pdf|bib|code|slides]
- Miryam de Lhoneux, Yan Shao, Ali Basirat, Eliyahu Kiperwasser, Sara Stymne, Yoav Goldberg, and Joakim Nivre. 2017. From raw text to Universal Dependencies - look, no tags! In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. [pdf|bib|code|poster]
- Miryam de Lhoneux, Sara Stymne and Joakim Nivre. Old School vs. New School: Comparing Transition-Based Parsers with and without Neural Network Enhancement. In Proceedings of the 15th Treebanks and Linguistic Theories Workshop (TLT), pages 99-110, 2017.
- Miryam de Lhoneux and Joakim Nivre. Should Have, Would Have, Could Have. Investigating Verb Group Representations for Parsing with Universal Dependencies. 2016. In Proceedings of the Workshop on Multilingual and Crosslingual Methods in NLP, pages 10-19. [pdf|bib|code|poster]
(best poster award)
- Miryam de Lhoneux, Omri Abend and Mark Steedman. To appear. Investigating the Effect of Automatic MWE Recognition on CCG Parsing. In Yannick Parmentier & Jakub Waszczuk (ed.). 2017. Representation and Parsing of Multiword Expressions: Current trends (Phraseology and Multiword Expressions 1).
- Miryam de Lhoneux. CCG Parsing and Multiword Expressions. 2014. Master's thesis. The University of Edinburgh. [pdf|bib|code]
- Miryam de Lhoneux. Towards a Systematic Contrastive Constructional Approach to the Resultative Construction: An Exploratory Study on English and French. 2013. Master's thesis, Université catholique de Louvain.
- Miryam de Lhoneux and Joakim Nivre. UD Treebank Sampling for Comparative Parser Evaluation. 2016. Presented at the Sixth Swedish Language Technology Conference (SLTC).
Note: There is a public abstract which is not archival. The material presented in the abstract was later published in our TLT 2017 paper (see reference above).
- Miryam de Lhoneux. Tree Transformations for Parsing: 2 Case Studies. Seminar given at Uppsala University, 7th June 2016. [slides]
- Miryam de Lhoneux. CCG Parsing and Multiword Expressions. Poster presented at the 4th general PARSEME meeting. Valletta, Malta. 2015. [poster|abstract]