no code implementations • WS 2019 • Jo{\~a}o Sedoc, Lyle Ungar
Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied.
no code implementations • NAACL 2019 • Jo{\~a}o Sedoc, Daphne Ippolito, Arun Kirubarajan, Jai Thirani, Lyle Ungar, Chris Callison-Burch
We introduce a unified framework for human evaluation of chatbots that augments existing tools and provides a web-based hub for researchers to share and compare their dialog systems.
no code implementations • ACL 2017 • Jo{\~a}o Sedoc, Jean Gallier, Dean Foster, Lyle Ungar
For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights.
no code implementations • EACL 2017 • Jo{\~a}o Sedoc, Daniel Preo{\c{t}}iuc-Pietro, Lyle Ungar
Inferring the emotional content of words is important for text-based sentiment analysis, dialogue systems and psycholinguistics, but word ratings are expensive to collect at scale and across languages or domains.