Research Assistant (Casual) at The University of Melbourne (Victoria, Australia), May, 2017–Aug, 2017
Research Duties: Responsible for implementing a bi-directional LSTM-CRF model for sequential tagging tasks in low-resource languages for the DARPA-funded LORELEI project in collaboration with CMU.
Research Intern at Xerox Research Centre Europe (Grenoble, France), May, 2016–Oct, 2016:
Research Topic and Achievements: Memory Networks, deep learning approach for personality trait recognition, 3 papers accepted at EACL 2017
Research Assistant (Casual) at Royal Melbourne Institute of Technology(Victoria, Australia), Sept, 2014–Feb, 2015:
Detailed Achievements: Customized Search Engine for Industry Partner. Managed to increase the accuracy of the query boundary detection process by 10% by applying machine learning techniques. Significantly improved the performance of the search engine (F-score from less than 10 to around 55 by boosting precision substantially and factoring in translation probabilities to detect paraphrases).
Bahar Salehi, Fei Liu, Timothy Baldwin and Wilson Wong (2018) Multitask Learning for Query Segmentation in Job Search. In Proceedings of the 8th International Conference on the Theory of Information Retrieval, Tianjin, China, pp. 179-182. Best Paper Award
Fei Liu and Julien Perez (2017) Gated End-to-End Memory Networks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, pp. 1-10.
Fei Liu, Alistair Moffat, Timothy Baldwin and Xiuzhen Zhang (2016) Quit while ahead: Evaluating truncated rankings. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Italy, pp. 953-956.
Julien Perez, Scott Nowson, Fei Liu. Author personality trait recognition from short texts with a deep compositional learning approach. US10049103B2 (granted).