Linguistic equations are designed for integrating knowledge and data in development of nonlinear multivariable systems for intelligent process analysis, process control, fault diagnosis and forecasting. Insight to the process operation is maintained since all the modules can be assessed by expert knowledge and membership definitions relate measurements to appropriate linguistic terms on differe...

The objective of the Unisys Spoken Language Systems effort is to develop and demonstra te technology for the understanding of goal-directed spontaneous speech. The Unisys spoken language architecture couples speech recognition systems with the Unisys discourse understanding system, PUNDIT. PUNDIT is a broad-coverage language understanding system used in a variety of message understanding applic...

The ability to recognize whether one text can be inferred from another is a critical element of various computational linguistics tasks. The current work explores what kind of linguistic information is useful, or even necessary, in making such inference judgments and how well an inference model using minimal representation and linguistic information performs on an inference judgment task.

Word alignment of bilingual parallel corpora is usually generated using only statistical information. External linguistic information like e.g. a dictionary or linguistic structural annotation of the texts is used rarely, despite its usefulness. Additionally, it has to our knowledge never been examined systematically how linguistic information can be employed for word alignment improvement. In ...

MuLLinG is a model for knowledge extraction (especially lexical extraction from corpora), based on multilevel graphs. Its aim is to allow large-scale data acquisition, by making it easy to realize automatically, and simple to configure by linguists with limited knowledge in computer programming. In MuLLinG, each new level represents the information in a different manner (more and more abstract)...

In this paper we present an iterative methodology to improve classifier performance by incorporating linguistic knowledge, and propose a way to incorporate domain rules into the learning process. We applied the methodology to the tasks of hedge cue recognition and scope detection and obtained competitive results on a publicly available corpus.

This paper describes the results of some experiments using a new approach to information access that combines techniques from natural language processing and knowledge representation with a penalty based technique for relevance estimation and passage retrieval. Unlike many attempts to combine natural language processing with information retrieval, these results show substantial benefit from usi...

We present work on the automatic generation of short indicative-informative abstracts of scientific and technical articles. The indicative part of the abstract identifies the topics of the document while the informative part of the abstract elaborate some topics according to the reader's interest by motivating the topics, describing entities and defining concepts. We have defined our method of ...

The present work describes a robust, high-capacity methodology for hiding secret information underneath a Modern Greek cover text by applying shallow syntactic transformations to it. Unlike similar approaches to linguistic steganography, the transformations are extracted automatically by making use of limited external resources, rendering the process easily portable to other free-phrase-order l...

We report three experiments that explore the effect of prior linguistic knowledge on implicit language learning. Native speakers of English and native speakers of Cantonese participated in implicit learning (IL) experiments that involved different learning materials. In Experiment 1, both participant groups showed evidence of learning a mapping between articles and noun animacy. In Experiment 2...