Data Set Used
The views, opinions, and/or findings contained in this report are those of the MITRE Corporation and should not be construed as an official Government position, policy, or decision, unless designated by other documentation.
We describe the treatment of questions (Question-Answer Typology, question parsing, and results) in the Weblcopedia question answering system.
We focus on developing an account of user behavior under error conditions, working with annotated data from real human-machine mixed initiative dialogs. In particular, we examine categories of error perception, user behavior under error, effect of user strategies on error recovery, and the role of user initiative in error situations. A conditional… (More)
In this short paper, I explore ways in which the MT community might formulate goals that will expand on known successes, build on existing strengths, and identify long term research goals.
SYSTRAN has demonstrated success in the MT field with its long history spanning nearly 30 years. As a general-purpose fully automatic MT system, SYSTRAN employs a transfer approach. Among its several components, large, carefully encoded, high-quality dictionaries are critical to SYSTRAN's translation capability. A total of over 2.4 million words and… (More)
We introduce a new generation of commercial translation software, based primarily on statistical learning and statistical language models. Language Weaver will begin licensing server-based machine translation software in September 2003. In addition to software licensing, Language Weaver offers system customization services. Windows servers and Windows XP… (More)
In Machine Translation (MT), output quality can be seriously affected by multi-sentence and multi-clause phenomena such as pronominalization, multisentence quotation, comma placement, etc. Yet almost all MT systems operate sentence-by-sentence. This paper describes the transfer of some research on paragraph structure from the research laboratory (USC/ISI)… (More)