Freda (Haoyue) SHI

Greetings! I am a third-year Ph.D. student at the Toyota Technological Institute at Chicago, advised by Prof. Karen Livescu and Prof. Kevin Gimpel. Prior to that, I received my B.S. degree from Peking University, China, where I did my undergraduate thesis with Prof. Junfeng Hu.

My research interests are in computational linguistics and natural language processing. I am particularly interested in structure of natural language and unsupervised learning methods; therefore, I have worked on

Unsupervised NLP methods, such as visually-grounded neural syntax learner (SMGL '19), bilingual lexicon induction from global statistics (SZW '20), and deep clustering methods for syntax induction (GSGS '20).

Analysis and improvement of existing NLP models, such as neural unsupervised parsing methods (SLG '20), contituency parse tree--based recursive neural networks (SZCL '18), visual-semantic embeddings (SMXJS '18), multi-sense word embeddings (SLH '16), and pretrained language models as text span representations (TSSGLG '20).

For more details, see my academic c.v.