Inducing Information Extraction, Ellen Riloff, Charles Schafer, David Yarowsky
Information extraction (IE) systems are costly to build because they require development texts, parsing tools, and specialized dictionaries for each application domain and each natural language that...
Combining Classiers for Word Sense Disambiguation (2007)
Radu Flor, I An, Charles Schafer
Classi er combination is an eective and broadly useful method of improving system performance. This article investigates in depth a large number of both well-established and novel classier...
Charles Schafer, David Yarowsky
{cschafer, yarowsky}}cs. jhu. edu This paper presents a method for inducing translation lexicons between two distant languages without the need for either parallel bilingual corpora or a direct...
Charles Schafer, David Yarowsky
This paper presents a method for inducing translation lexicons between two distant languages without the need for either parallel bilingual corpora or a direct bilingual seed dictionary. The...
Models for Inuktitut-English Word Alignment (2005)
Charles Schafer, Elliott Franco Drabek
This paper presents a set of techniques for bitext word alignment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual affinities...
JHU 2004 Machine Translation Evaluation Systems – p.3/24 (2004)
Shankar Kumar, Yonggang Deng, Charles Schafer, Woosung Kim, Paola Virga, Nizar Habash, ...
Interested in WFST techniques from work in ASR
JHU 2004 Machine Translation Evaluation Systems – p.3/24 (2004)
Shankar Kumar, Yonggang Deng, Charles Schafer, Woosung Kim, Paola Virga, Nizar Habash, ...
Interested in WFST techniques from work in ASR
Statistical machine translation using coercive two-level syntactic transduction (2003)
Charles Schafer, David Yarowsky
We define, implement and evaluate a novel model for statistical machine translation, which is based on shallow syntactic analysis (part-of-speech tagging and phrase chunking) in both the source and...
Combining classifiers for word sense disambiguation (2002)
Radu Florian, Silviu Cucerzan, Charles Schafer
Classifier combination is an e#ective and broadly useful method of improving system performance. This article investigates in depth a large number of both well-established and novel classifier...
The Johns Hopkins SENSEVAL2 system descriptions (2001)
David Yarowsky, Silviu Cucerzan, Radu Florian, Charles Schafer, Richard Wicentowski
This article describes the Johns Hopkins University (JHU) sense-disambiguation systems that participated in seven SENSEVAL2 tasks: four supervised lexical choice systems (Basque, English, Spanish,...