Student research opportunities
Learning to learn Multi-word expressions errors
Project Code: CECS_1150
This project is available at the following levels:
Engn R&D, Honours, Summer Scholar
Please note that this project is only for undergraduate students.
Keywords:
Natural Language Processing, Machine Learning, Lexical Errors, Collocation Errors, Computer Assist Language Learning
Supervisors:
Dr Gabriela FerraroDr Lizhen Qu
Outline:
Learning the correct use of Multi-word expressions is one of the most difficult tasks that the student faces when learning a second language, for example, "make a difference" vs. "do a difference". The goal of this project is to apply Natural Language Processing and Machine Learning Techniques to develop a system that is able to predict whether a given word combination is a valid Multi-word expressions in the language in question or not, and to suggest a correction.
Requirements/Prerequisites
Familiarized with Machine Learning. Good coding skills in Java. Scala coding is a plus!
Background Literature
The CoNLL-2013 Shared Task on Grammatical Error Correction. Hwee Tou Ng and Siew Mei Wu and Yuanbin Wu and Christian Hadiwinoto and Joel Tetreault. 2013.
Multiword expressions: A pain in the neck for NLP
IA Sag, T Baldwin, F Bond, A Copestake, D Flickinger
Computational Linguistics and Intelligent Text Processing, 1-15
