• Publications
  • Influence
Transliteration of Proper Names in Cross-Lingual Information Retrieval
TLDR
We demonstrate statistical machine translation techniques to "translate" the phonemic representation of an English name, obtained by using an automatic text-to-speech system, to a sequence of initials and finals, commonly used sub-word units of pronunciation for Chinese. Expand
  • 186
  • 10
  • PDF
Joint visual-text modeling for automatic retrieval of multimedia documents
TLDR
We propose a novel approach for jointly modeling the text and the visual components of multimedia documents for the purpose of information retrieval(IR). Expand
  • 47
  • 2
  • PDF
Transliteration of proper names in cross-language applications
TLDR
This research was partially supported by DARPA via Grant N66001-00-2-8910 and ONR via Grant No N00014-01-1-0685. Expand
  • 45
  • 1
Fast semi-automatic semantic annotation for spoken dialog systems
TLDR
This paper describes a bootstrapping methodology for semi– automatic semantic annotation of a “mini–corpus” that is conventionally annotated manually to train an initial parser used in natural language understanding (NLU) systems. Expand
  • 4
  • 1
  • PDF
RADSAR (RADiometric SAR) experimental results
TLDR
The military and the meteorological communities have long sought an all-weather, day-night, passive means of imaging terrain, rain, sea surface and atmospheric conditions. Expand
  • 6
  • 1
The Johns Hopkins University 2003 Chinese-English Machine Translation System
TLDR
We describe a Chinese to English Machine Translation system developed at Johns Hopkins University for the NIST 2003 MT evaluation. Expand
  • 12
  • 1
  • PDF
Systematic Evaluation of Machine Translation Methods for Image and Video Annotation
TLDR
We present a systematic evaluation of machine translation methods applied to the image annotation problem. Expand
  • 17
  • PDF
Aggregating distributed STT, MT, and information extraction engines: the GALE interoperability-demo system
TLDR
The GALE Interoperability Demo system consists of 12 engines including speech recognition, translation, and various information extraction engines, interoperated to make Arabic news video browsable as English text grouped and summarized by topic. Expand
  • 7
  • PDF
Joint Visual-Text Modeling for Multimedia Retrieval
  • 4
MAAI: Media analytics for actionable intelligence
TLDR
MAAI is a combination of automatic, semi-automatic and manual tools which provide three basic levels of analysis: automatic services, manual feedback, and higher level mining (e.g. timeline, social network, hypothesis generation). Expand