CORR
2000
Springer
13 years 4 months ago
2000
Springer
The multidimensional, heterogeneous, and temporal nature of speech databases raises interesting challenges for representation and query. Recently, annotation graphs have been prop...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
We describe a formal model for annotating linguistic artifacts, from which we derive an application programming interface (API) to a tools for manipulating these annotations. The ...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
This paper describes a new method, COMBI-BOOTSTRAP, to exploit existing taggers and lexical resources for the annotation of corpora with new tagsets. COMBI-BOOTSTRAP uses existing...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
In this paper Schapire and Singer's AdaBoost.MH boosting algorithm is applied to the Word Sense Disambiguation (WSD) problem. Initial experiments on a set of 15 selected polys...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
Finite-state morphology in the general tradition of the Two-Level and Xerox implementations has proved very successful in the production of robust morphological analyzer-generator...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
This paper presents a semantic parsing approach for non domain-specific texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
Previous work (Frank and Satta, 1998; Karttunen, 1998) has shown that Optimality Theory with gradient constraints generally is not finite state. A new finite-state treatment of gr...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and topic units. Speech segm...
CORR
2000
Springer
13 years 4 months ago
2000
Springer
CORR
2000
Springer
13 years 4 months ago
2000
Springer
It has recently been argued that a Naive Bayesian classifier can be used to filter unsolicited bulk e-mail ("spam"). We conduct a thorough evaluation of this proposal on...