Learn More
It is often remarked that natural language, used naturally, is unnaturally ungrammatical.* Spontaneous speech contains all manner of false starts, hesitations, and self-corrections that disrupt the well-formedness of strings. It is a mystery then, that despite this apparent wide deviation from grammatical norms, people have little difficx:lty understanding(More)
This paper reports experimental results comparing a mixed-initiative to a system-initiative dialogue strategy in the context of a personal voice email agent. To independently test the effects of dialogue strategy and user expertise, users interact with either the system-initiative or the mixed-initiative agent to perform three successive tasks which are(More)
Linguists, including computational linguists, have always been fond of talking about trees. In this paper, we outline a theory of linguistic structure which talks about talking about trees; we call this theory Description theory (D-theory). While important issues must be resolved before a complete picture of D-theory emerges (and also before we can build(More)
There are a number of coUocational constraints in natural languages that ought to play a more important role in natural language parsers. Thus, for example, it is hard for most parsers to take advantage of the fact that wine is typically drunk, produced, and sold, but (probably) not pruned. So too, it is hard for a parser to know which verbs go with which(More)
The problem of quantitatively comparing tile performance of different broad-coverage grammars of En-glish has to date resisted solution. Prima facie, known English grammars appear to disagree strongly with each other as to the elements of even tile simplest sentences. For instance, the grammars of Steve Abneying), Don tfindle (AT&T), Bob Ingria (BBN), and(More)
This paper presents experimental results comparing two different designs for a spoken language interface to email. We compare a mixed-initiative dialogue style, in which users can flexibly control the dialogue, to a system-initiative dialogue style, in which the system controls the dialogue. Our results show that even though the mixed-initiative system is(More)
We combine our earlier approach to context-dependent network representation with our algorithm for determinizing weighted networks to build optimized networks for large-vocabulary speech recognition combining an n-gram language model, a pronunciation dictionary and context-dependency modeling. While fully-expanded networks have been used before in(More)