Publications



Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings

Manzini, Lim, Tsvetkov, Black

NAACL-HLT ’19. The Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Minneapolis, Minnesota, USA


Black is to Criminal as Caucasian is to Police - Detecting and Removing Multi Class Bias in Word Embeddings

Paper Presentation Repository


Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities

Pham, Liang, Manzini, Morency, Póczos

AAAI ’19. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence

Honolulu, Hawaii, USA


Found in Translation Learning Robust Joint Representations by Cyclic Translations Between Modalities

Paper Presentation Poster Repository


Towards Improving the Intelligibility of Black-Box Speech Synthesizers in Noise

Manzini, Black

SPECOM ’18. Proceedings of the 20th International Conference on Speech and Computer

Leipzig, Germany


Towards Improving the Intelligibility of Black-Box Speech Synthesizers in Noise

Paper Presentation Dataset


Language Informed Modeling of Code-Switched Text

Manzini, Chandu, Singh

ACL ’18. Proceedings of the 56th conference of the Association of Computational Linguistics

Workshop on Computational Approaches to Linguistic Code-switching

Melbourne, Victoria, Australia


Language Informed Modeling of Code Switched Text

Paper Poster


Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis

Manzini, Pham, Liang, Póczos.

ACL ’18. Proceedings of the 56th conference of the Association of Computational Linguistics

Workshop on Human Multimodal Language (Oral)

Melbourne, Victoria, Australia


Seq2Seq2Sentiment - Multimodal Sequence to Sequence Models for Sentiment Analysis

Paper Presentation Repository


Building CMU Magnus from User Feedback

Prabhumoye, Botros, Chandu, Choudhary, Keni, Malaviya, Manzini, Pasumarthi, Poddar & Ravichander et al.

In AWS re:INVENT 2017.

Alexa Prize '17.

Las Vegas, NV, USA.


Building CMU Magnus from User Feedback

Paper


How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing

Manzini, Ravichander, Grabmair, Neubig, Francis, Nyberg.

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue Association for Computational Linguistics

Saarbrcken, Germany


How Would You Say It - Eliciting Lexically Diverse Data for Supervised Semantic Parsing (07-07-2017)

Paper Poster Dataset


A Play on Words: Using Cognitive Computing as a Basis for AI Solvers in Word Puzzles

Manzini, Ellis, & Hendler

Special Issue on Computational Creativity, Concept Invention, and General Intelligence.

Journal of Artificial General Intelligence.


A Play on Words Using Cognitive Computing as a Basis for AI Solvers in Word Puzzles

Paper Poster