Traditional approaches to the problem of extracting data from texts have emphasized handcrafted linguisti c knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of a DARPA-funded research effort on integrating probabilistic language models with more traditiona l linguistic techniques . Our research and development goals are • more rapid de...

Interpreting fttUy natural speech is an important goal for spoken language understanding systems. However, while corpus studies have shown that about 10% of spontaneous utterances contain selfcorrections, or REPAIRS, little is known about the extent to which cues in the speech signal may facilitate repair processing. We identify several cues based on acoustic and prosodic analysis of repairs in...

Certain content of a linguistic construction can project when the construction is embedded in entailment-canceling environments. For example, the conclusion that John smoked in the past from the utterance John stopped smoking still holds for John didn’t stop smoking, in which the original utterance is embedded under negation. There are two main approaches to account for projection phenomena. Th...

The sixth in a series of "Message Understanding Conferences", which are designed to promote and evaluate research in information extraction, was held last fall. MUC-6 introduced several innovations over prior MUCs, most notably in the range of different tasks for which evaluations were conducted. We describe the development of the "message understanding" task over the course of the prior MUCs, ...

T h e aim o f t h is disse rt at io n is t o ide nt ify h o w t h e spe c t rum c urre nt l y al l o c at e d fo r T V bro adc ast ing c an be re use d by so me o t h e r c o mmunic at io n syst e ms. T h e spe c t rum re use is al l o w e d o nl y if t h e c urre nt T V use rs are no t dist urbe d. T h e st udy addre sse s t h e pro bl e ms o f h o w t h e se c o ndary ac c e ss t o t h e spe ...

We address the problem of extracting Minimal Unsatisfiable Cores (MUCs) from constraint networks. This computationally hard problem has a practical interest in many application domains such as configuration, planning, diagnosis, etc. Indeed, identifying one or several disjoint MUCs can help circumscribe different sources of inconsistency in order to repair a system. In this paper, we propose an...

We investigate the understanding of landmarks using a model of embedding procedures that sees affordances established on three levels. On the first level there are landmark experience and direct communication process as distinct affordance structures. On the second level the initial landmark experience has become part of the speech act thus establishing direct wayfinding communication. On the t...

This paper describes a robust parsing algorithm for spoken language understanding. Comparing with the other work in robust parsing, we focus on building a parser that is robust to not only ill-formed spontaneous spoken language inputs but also under-specified grammars. Preliminary experiment results show that the parsing performance deteriorates more gracefully than another parser we have used ...