• Publications
  • Influence
Automatic evaluation of machine translation quality using n-gram co-occurrence statistics
Evaluation is recognized as an extremely helpful forcing function in Human Language Technology R&D. Expand
The Automatic Content Extraction (ACE) Program - Tasks, Data, and Evaluation
The objective of the ACE program is to develop technology to automatically infer from human language data the entities being mentioned, the relations among these entities that are directly expressed, and the events in which these entities participate. Expand
Topic Detection and Tracking Pilot Study Final Report
Topic Detection and Tracking (TDT) is a DARPA-sponsored initiative to investigate the state of the art in finding and following new events in a stream of broadcast news stories. The TDT problemExpand
The ATIS Spoken Language Systems Pilot Corpus
We describe the Air Travel Information System (ATIS) pilot corpus, a corpus designed to measure progress in Spoken Language Systems that include both a speech and natural language component. Expand
The DET curve in assessment of detection task performance
We introduce the DET Curve as a means of representing performance on detection tasks that involve a tradeoff of error types. Expand
SHEEP, GOATS, LAMBS and WOLVES: a statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation
We propose statistical tests for the existence of animal names for different types of speakers, including sheep, goats, lambs and wolves, depending on their behavior with respect to automatic recognition systems. Expand
The NIST speaker recognition evaluation - Overview, methodology, systems, results, perspective
This paper, based on three presentations made in 1998 at RLA2C Workshop in Avignon, discusses the evaluation of speaker recognition systems from several perspectives. Expand
Speaker recognition based on idiolectal differences between speakers
“Familiar” speaker information is explored using non-acoustic features in NIST’s speaker detection task.[1] Word unigrams and bigrams, used in a traditional target/background likelihood ratio framework, give surprisingly good performance. Expand
Speaker recognition—Identifying people by their voices
The usefulness of identifying a person from the characteristics of his voice is increasing with the growing importance of automatic information processing and telecommunications. This paper reviewsExpand
Topic detection and tracking evaluation overview
The objective of the Topic Detection and Tracking (TDT) program is to develop technologies that search, organize and structure multilingual, news oriented textual materials from a variety of broadcast news media. Expand