I finished my PhD in Computer Science at the University of Maryland, College Park in May 2010. My PhD advisor was Bonnie Dorr. I am currently a post-doctoral researcher and adjunct faculty at CUNY, Queens College in the BLENDER lab, working on Information Extraction, as well as on Machine Translation and Speech Recognition in the GALE program. My current research focuses on information extraction, statistical machine translation, disfluency detection in conversation speech and machine translation evaluation.

I did my Master's work at Washington University in St. Louis in the department of Computer Science with Michael Brent, working on the unsupervised learning of morphology.
 
My research interests are in Computational Linguistics, Statistical Machine Translation, Information Extraction, Machine Learning, Unsupervised and Minimally Supervised Learning, Evaluation Metrics for Natural Language Processing, and Artificial Intelligence.

• Spring 2011: Natural Language Processing (CS 3813/780)

Journal Papers

• TER-Plus: paraphrase, semantic, and alignment enhancements to Translation Edit Rate [link]
  Matthew Snover, Nitin Madnani, Bonnie J. Dorr, and Richard Schwartz.
  Machine Translation, 23(2-3) 117-127, Springer Netherlands, 2010.
• Expected dependency pair match: predicting translation quality with expected syntactic structure [link]
  Jeremy G. Kahn, Matthew Snover, and Mari Ostendorf.
  Machine Translation, 23(2-3) 169-179, Springer Netherlands. 2010.

Conference Papers

• Fluency, Adequacy, or HTER? Exploring Different Human Judgments with a Tunable MT Metric [PDF]
  Matthew Snover, Nitin Madnani, Bonnie J. Dorr, and Richard Schwartz.
  Proceedings of the Fourth Workshop on Statistical Machine Translation at the 12th Meeting of the European Chapter of the Association for Computational Linguistics (EACL-2009), 2009.
• Language and Translation Model Adaptation using Comparable Corpora [PDF] [Slides PDF]
  Matthew Snover, Bonnie J. Dorr, and Richard Schwartz.
  Proceedings of the Conference on Empirical Methods in Natural Language Processing 2008 (EMNLP 2008), 2008.
• A Study of Translation Edit Rate with Targeted Human Annotation [PDF] [Slides PDF] [Slides PPT]
  Matthew Snover, Bonnie J. Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul.
  Proceedings of Association for Machine Translation in the Americas, 2006.
• PCFGs with Syntactic and Prosodic Indicators of Speech Repairs [PDF]
  John Hale, Izhak Shafran, Lisa Yung, Bonnie Dorr, Mary Harper, Anna Krasnyanskaya, Matthew Lease, Yang Liu, Brian Roark, Matthew Snover, and Robin Stewart
  Proceedings of the Association of Computational Linguistics 2006 (ACL 2006), 2006.
• Reranking for Sentence Boundary Detection in Conversational Speech [PDF]
  Brian Roark, Yang Liu, Mary Harper, Robin Stewart, Matthew Lease, Matthew Snover, Izhak Shafran, Bonnie J. Dorr, John Hale, Anna Krasnyanskaya, and Lisa Yung,
  Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2006), Toulouse France, 2006.
• Sparseval: Evaluation Metrics for Parsing Speech [PDF]
  Brian Roark, Mary Harper, Eugene Charniak, Bonnie J. Dorr, Mark Johnson, Jeremy G. Kahn, Yang Liu, Mari Ostendorf, John Hale, Anna Krasnyanskaya, Matthew Lease, Izhak Shafran, Matthew Snover, Robin Stewart, and Lisa Yung,
  Proceedings of the International conference on Language Resources and Evaluation (LREC 2006), Genoa, Italy, 2006.
• RT-S: Surface Rich Transcription Scoring, Methodology, and Initial Results [PDF]
  Matthew Snover, Richard Schwartz, Bonnie Dorr, and John Makhoul, 2004.
  Proceedings of the Rich Transcription 2004 Workshop.
• A Lexically-Driven Algorithm for Disfluency Detection [PDF]
  Matthew Snover, Bonnie Dorr, and Richard Schwartz, 2004.
  Short Paper Proceedings of North American Association for Computational Linguistics (NAACL) and Human Language Technology (HLT) Conference 2004
• A Probabilistic Model for Learning Concatenative Morphology [PS] [PDF] [POSTER PDF]
  Matthew Snover and Michael Brent. 2002.
  Proceedings of NIPS 2002.
• Unsupervised Learning of Morphology Using a Novel Directed Search Algorithm: Taking the First Step [PS] [PDF]
  Matthew Snover, Gaja Jarosz, and Michael Brent. 2002.
  Association for Computational Linguistics (ACL-2002): Workshop on Morphological and Phonological Learning.
• A Bayesian Model for Morpheme and Paradigm Identification [PS] [PDF]
  Matthew Snover and Michael Brent. 2001.
  Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-2001), pages 482-490.

Theses

• An Unsupervised Knowledge Free Algorithm for the Learning of Morphology in Natural Languages [PS] [PDF]
  Matthew Snover. 2002.
  Washington University MS Thesis
  Thesis Committee: Michael Brent, Sally Goldman, and Stan Kwasny.

Technical Reports and Others

• Final Report on Parsing and Spoken Structural Event Detection [PDF]
  Harper, Mary Harper, Bonnie J. Dorr, John Hale, Brian Roark, Izhak Shafran, Matthew Lease, Yang Liu, Matthew Snover, Lisa Yung, Anna Krasnyanskaya, Robin Stewart, "Final Report on Parsing and Spoken Structural Event Detection", 2005 Johns Hopkins Summer Workshop, 2005.
• A Study of Translation Error Rate with Targeted Human Annotation [PDF]
  Snover, Matthew, Bonnie J. Dorr, Richard Schwartz, John Makhoul, Linnea Micciulla, Ralph Weischedel, "A Study of Translation Error Rate with Targeted Human Annotation," LAMP-TR-126, CS-TR-4755, UMIACS-TR-2005-58, University of Maryland, College Park, MD July, 2005.

Software

• Translation Error Rate (TER) Computation [Software Page]
  I have written several pieces of code to compute Translation Error Rate (or TER), an error measure for machine translation that is currently in use in the GALE research program. This code has been adopted by NIST as the official evaluation software.
• TER-Plus (TERp) [Software Page]
  An enhancement to TER that uses morphological information, synonymy, paraphrases, and optimized edit costs to improve correlation with human judgments of translation quality.

Matthew G. Snover / snover@cs.umd.edu