We propose a new method for detecting errors in "gold-standard" part-ofspeech annotation. The approach locates errors with high precision based on n-grams occurring in the corpus with multiple taggings. Two further techniques, closed-class analysis and finitestate tagging guide patterns, are discussed. The success of the three approaches is illustrated for the Wall Street Journal corpus as part...

*Performed under the auspices of the US Department of Energy by Lawrence Livermore National Laboratory under contract No. W-7405-Eng-48. a)Consultant. b)Present affiliation: Voss Scientific, 416 Washington Street SE, Albuquerque, NM 87108. Figure 2. Breakdown thresholds for 0 o vacuum insulators. Figure 1. Dielectric Wall Accelerator (DWA). HIGH GRADIENT INSULATOR TECHNOLOGY FOR THE DIELECTRIC ...

This paper considers statistical parsing of Czech, which differs radically from English in at least two respects: (1) it is a highly inflected language, and (2) it has relatively free word order. These differences are likely to pose new problems for techniques that have been developed on English. We describe our experience in building on the parsing model of (Collins 97). Our final results – 80...

For all its hard won success, by the beginning of the last decade of the twentieth century, feminism was troubled. Though younger, less visible, and less institutionalized, the lesbian and gay rights movement also had made some great advances over the previous few decades, yet it, too, was fraught. There was the serious, but more obvious problem that many women and gay men and lesbians—persons ...

In this paper) we propose a method for text categorizaLion task using term weight learning. In our approach, learning is to learn true keywords from the error of clustering results. Parameters of term weighting are then estimated so as to maximize the true keywords and minimize the other words in the text. The characteristic of our approach is that the degree of context dependency is used in or...

The problem considered is credential exchange between strangers when credentials are sensitive. A framework is presented for negotiating the exchange of sensitive property-based credentials that are exchanged to establish trust between clients and servers. The notion of a trust negotiation strategy is introduced and two strategies with very different properties are discussed. This article is ex...

This paper proposes a series of techniques for extracting English verb–particle constructions from raw text corpora. We initially propose three basic methods, based on tagger output, chunker output and a chunk grammar, respectively, with the chunk grammar method optionally combining with an attachment resolution module to determine the syntactic structure of verb–preposition pairs in ambiguous ...

Arrau is a new corpus annotated for anaphoric relations, with information about agreement and explicit representation of multiple antecedents for ambiguous anaphoric expressions and discourse antecedents for expressions which refer to abstract entities such as events, actions and plans. The corpus contains texts from different genres: task-oriented dialogues from the Trains-91 and Trains-93 cor...

We combine lexical, syntactic, and discourse features to produce a highly predictive model of human readers’ judgments of text readability. This is the first study to take into account such a variety of linguistic factors and the first to empirically demonstrate that discourse relations are strongly associated with the perceived quality of text. We show that various surface metrics generally ex...

During the last few years our secretaries have been so active in organizing interesting programs at the regular meetings that surveys of progress in the more important fields of mathematics have been presented to the Society quite recently. At the meeting last April in New York, reports on Algebraic Geometry were given. I have therefore felt impelled to change in some measure the traditional ch...