I am a Ph.D. student at the University of Pennsylvania. Professor Chris Callison-Burch is my advisor. My research area is Computational Linguistics, or Natural Language Processing (NLP). Specifically, I have great passion towards the subarea Machine Translation, especially the topic of domain adaptation. My research involves many interesting topics in NLP, such as hierarchical text clustering, building machine translation models, exploration of parallel translation from comparable corpora, etc.
Currently, I have been doing a project that aims to cluster adjectives from Paraphrase Database (PPDB). Many of the adjectives can be lined up on a scale and get scored, so we call them scalar adjectives. Clustering and getting measurement of scalar adjectives are beneficial from many aspects. For example, it could help with the semantic understanding of sentences and contributes to other NLP topics like Aspect-based Sentiment Analysis. During the experiments, we collected valuable data for evaluation with Crowdsourcing, which is also an interesting and an emerging field. And it is always a nice and practical tool that can help acquire good research data.
University of Pennsylvania (Current, Ph.D. Student)
Columbia University (Feb. 2016, Master of Science)
Beijing University of Technology (Jul. 2013, Bachelor of Science)
Agricultural Bank of China
Teaching Assistant at the University of Pennsylvania
Undergrad Mentoring at the University of Pennsylvania
- Prediction of a hotspot pattern in keyword search results. , Axinia Radeva, Chuyao Shen, Shiqi Wang, Qianbo Wang, Rebecca Passonneau. Computer speech & language, 2018, Vol.48.
- Learning Translations via Matrix Completion. Derry Wijaya, Brendan Callahan, John Hewitt, , Xiao Ling, Marianna Apidianaki and Chris Callison-Burch. EMNLP 2017.