My current work focuses on applying techniques from natural language processing to data from businesses, typically chat and emails, although I have also worked wire transaction records, call center records, and other sorts of data. Some of the tasks I've worked on are: language identification in noisy documents, OCR error detection, document classification, and developing tools to help identify fraud or compliance risks. I am currently employed as a Senior Data Scientist at RedOwl, and before that I worked in this area as a Senior in the Fraud Investigation and Dispute Services group at EY.
My dissertation research focused on detecting and classifying grammatical errors in transcripts of spoken language collected from children, some of whom may have developmental disorders that result in impaired language. I worked on a project to automatically identify disfluencies and certain types of grammatical errors in transcripts of spoken language collected from children with autism spectrum disorders and specific language impairment. I also investigated which, if any, of these grammatical errors may be diagnostically informative.
Before coming to natural lanugage processing, my previous research included: prosodic modeling and analysis, particularly for speech synthesis; phonology; and documenting Ajagbe, a language spoken in Benin.
Kyle Gorman, Steven Bedrick, Géza Kiss, Eric Morley, Rosemary Ingham, Metrah Mohammed, Katina Papadakis and Jan van Santen. Automated morphological analysis of clinical language samples. In Proceedings of the ACL-HLT 2015 2nd Workshop on Computational Linguistics and Clinical Psychology (CLPsych), 2015.
Emily Prud'hommeaux, Eric Morley, Masoud Rouhizadeh, Laura Silverman, Jan van Santen, Sarah Kauper, and Rachel DeLaHunta. Computational Analysis of Trajectories of Linguistic Development in Autism. In Proceedings of the IEEE Spoken Language Technology Workshop (SLT), 2014.
Eric Morley, Anna Eva Hallin, and Brian Roark. Data Driven Grammatical Error Detection in Transcripts of Children's Speech. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
Eric Morley, Anna Eva Hallin, and Brian Roark. Challenges in Automating Maze Detection. In Proceedings of the ACL-HLT 2014 1st Workshop on Computational Linguistics and Clinical Psychology (CLPsych), 2014.
Eric Morley, Brian Roark, and Jan van Santen. The Utility of Manual and Automatic Linguistic Error Codes for Identifying Neurodevelopmental Disorders. In Proceedings of the NAACL-HLT 2013 8th Workshop on Innovative Use of NLP for Building Educational Applications (BEA8), 2013.
Amjad Abu-Jbara, Rahul Jha, Eric Morley, and Dragomir Radev. Experimental Results on the Native Language Identification Shared Task. In Proceedings of the NAACL-HLT 2013 8th Workshop on Innovative Use of NLP for Building Educational Applications (BEA8), 2013.
Eric Morley and Emily Prud'hommeaux. Using constituency and dependency parse features to identify errorful words in disordered language. In Proceedings of the 3rd Workshop on Child, Computer and Interaction (WOCCI 2012), 2012.
Eric Morley, Esther Klabbers, Jan van Santen, Alexander Kain, and Seyed Hamidreza Mohammadi. Synthetic F0 can Effectively Convey Speaker ID in Delexicalized Speech. In Proceedings of the 13th Annual Conference of the International Speech Communication Association (Interspeech), 2012.
Eric Morley, Jan van Santen, Ean Klabbers, and Alexander Kain. F0 Range and Peak Alignment across Speakers and Emotions. In Proceedings of the 36th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2011.