HLTCOE: An academic research center for HLT

Syntactic translation models improve reordering between Urdu-English

Building knowledge databases from human language

Restoring Incorrectly Demodulated Radio Speech

Joshua: A syntactically informed machine translation system

Twitter Tracks the Flu: Researchers Find a Better Way to Screen Tweets

News

2013.04.26 | HLTCOE Hires Gregory Sell
The HLTCOE has hired Gregory Sell as a Research Scientist.... [more]

[ Read all News ]

Featured Researcher

Daniel Garcia-Romero Daniel Garcia-Romero
<p>Senior Research Scientist. Automatic speaker and language recognition, machine learning, and information forensics.</p>

[ Read more about Daniel ]

Recent Publications

Answer Extraction as Sequence Tagging with Tree Edit Distance
Xuchen Yao, Benjamin Van Durme, Peter Clark and Chris Callison-Burch. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Generating Expressions that Refer to Visible Objects
Margaret Mitchell, Kees van Deemter and Ehud Reiter. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs
Hua He, Jimmy Lin and Adam Lopez. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Supervised Bilingual Lexicon Induction with Multiple Monolingual Signals
Ann Irvine and Chris Callison-Burch. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

PPDB: The Paraphrase Database
Juri Ganitkevitch, Benjamin Van Durme and Chris Callison-Burch. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Broadly Improving User Classification via Communication-Based Name and Location Clustering on Twitter
Shane Bergsma, Mark Dredze, Benjamin Van Durme, Theresa Wilson and David Yarowsky. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

What's in a Domain? Multi-Domain Learning for Multi-Attribute Data
Mahesh Joshi, Mark Dredze, William Cohen and Carolyn P. Rose. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Separating Fact from Fear: Tracking Flu Infections on Twitter
Alex Lamb, Michael Paul and Mark Dredze. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Drug Extraction from the Web: Summarizing Drug Experiences with Multi-Dimensional Topic Models
Michael Paul and Mark Dredze. North American Chapter of the Association for Computational Linguistics (NAACL) – 2013.

Estimating Confusions in the ASR Channel for Improved Topic-based Language Model Adaptation
Damianos Karakos, Mark Dredze and Sanjeev Khudanpur. 2013.

[ View all Publications ]