I develop computational models of natural language learning, understanding and generation in people and machines, and my research focuses on basic scientific, mathematical, and engineering problems related to these models. I am especially interested in models that handle the diversity of morphological, syntactic, and semantic phenomena across the world’s languages. My research group is part of the larger Edinburgh natural language processing group, and we collaborate with many people in Edinburgh and more widely. I am also the deputy director of the Centre for Doctoral Training in Data Science, which offers a four-year MSc + PhD programme.

Recent Highlights

Parsing graphs with regular graph grammars
Sorcha Gilroy, Adam Lopez, and Sebastian Maneth. In Proceedings of *SEM, 2017.
Abstract
(Re)introducing regular graph languages
Sorcha Gilroy, Adam Lopez, Sebastian Maneth, and Pijus Simonaitis. In Meeting on the Mathematics of Language, 2017.
Abstract
From characters to words to in between: Do we capture morphology?
Clara Vania and Adam Lopez. In Proceedings of ACL, 2017.
Abstract
A generative parser with a discriminative recognition algorithm
Jianpeng Cheng, Adam Lopez, and Mirella Lapata. In Proceedings of ACL, 2017.
Abstract
Detecting negation scope is easy, except when it isn't
Federico Fancellu, Adam Lopez, Bonnie Webber and Hangfeng He. In Proceedings of EACL, 2017.
Abstract
Towards speech-to-text translation without speech recognition
Sameer Bansal, Adam Lopez, Herman Kamper, and Sharon Goldwater. In Proceedings of EACL, 2017.
Abstract
Weakly supervised spoken term discovery using cross-lingual side information
Sameer Bansal, Herman Kamper, Sharon Goldwater, and Adam Lopez. In Proceedings of ICASSP, 2017.
Abstract
Evaluating informal-domain word representations with UrbanDictionary
Naomi Saphra and Adam Lopez. In Proceedings of RepEval, 2016.
Abstract Code
N-gram language models for massively parallel devices
Nikolay Bogoychev and Adam Lopez. In Proceedings of ACL, 2016.
Abstract Code