Search Results for author: Thomas Manzini

Found 5 papers, 2 papers with code

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

2 code implementations19 Dec 2018 Hai Pham, Paul Pu Liang, Thomas Manzini, Louis-Philippe Morency, Barnabas Poczos

Our method is based on the key insight that translation from a source to a target modality provides a method of learning joint representations using only the source modality as input.

Machine Translation Multimodal Sentiment Analysis +1

Language Informed Modeling of Code-Switched Text

no code implementations WS 2018 Ch, Khyathi u, Thomas Manzini, Sumeet Singh, Alan W. black

Code-switching (CS), the practice of alternating between two or more languages in conversations, is pervasive in most multi-lingual communities.

Machine Translation Speech Recognition

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

no code implementations WS 2017 Ravich, Abhilasha er, Thomas Manzini, Matthias Grabmair, Graham Neubig, Jonathan Francis, Eric Nyberg

Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording.

Semantic Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.