I’m a PhD student in computer science at the University of Washington, studying natural language processing and advised by Noah Smith as part of Noah’s Ark.
My work focuses on multilingual NLP: learning how to do NLP in languages other than English and developing methods that generalize across many languages. I’m particularly interested in ways to use knowledge from one language to improve our understanding of another. Some projects include methods for producing multilingual word vectors, neural language identification, and multilingual semantic role labeling.
Before starting my PhD I studied computer science and cognitive science at UC Berkeley and did undergraduate research with Pieter Abbeel.
You can contact me at pmulc at cs dot washington dot edu.
Low-Resource Parsing with Crosslingual Contextualized Representations. Phoebe Mulcaire, Jungo Kasai, and Noah A. Smith. Proceedings of CoNLL 2019.
Polyglot Contextual Representations Improve Crosslingual Transfer. Phoebe Mulcaire, Jungo Kasai, and Noah A. Smith. Proceedings of NAACL 2019. (models, code)
Polyglot Semantic Role Labeling. Phoebe Mulcaire, Swabha Swayamdipta, and Noah A. Smith. Proceedings of ACL 2018.
A Neural Model for Language Identification in Code-Switched Tweets. Aaron Jaech, Phoebe Mulcaire, Mari Ostendorf, and Noah A. Smith. Proceedings of LICS 2016.
Hierarchical Character-Word Models for Language Identification. Aaron Jaech, Phoebe Mulcaire, Shobhit Hathi, Mari Ostendorf, and Noah A. Smith. Proceedings of SocialNLP 2016.
Many Languages, One Parser. Waleed Ammar, Phoebe Mulcaire, Miguel Ballesteros, Chris Dyer, and Noah A. Smith. TACL 4:431–444, July 2016.
Massively Multilingual Word Embeddings. Waleed Ammar, Phoebe Mulcaire, Yulia Tsvetkov, Guillaume Lample, Chris Dyer, and Noah A. Smith. 2016.