Previous work [Gale, Church and Yarowsky, 1992] showed that with high probability a polysemous word has one sense per discourse. In this paper we show that for certain definitions of collocation, a polysemous word exhibits essentially only one sense per collocation. We test this empirical hypothesis for several definitions of sense and collocation, and discover that it holds with 90-99% accurac...

Cognitive semio-linguistics studies the relations between signs and language, between semiological and linguistic structures, as expressions of, and as causes of, the cognitive activities involved in thinking, here called epistemic activities. This short essay displays a leveled analysis of the relations holding between semio-linguistic and epistemic structures active in the human mind. 1. Semi...

We report in this paper the observation of one tokenization per source. That is, the same critical fragment in different sentences from the same source almost always realize one and the same of its many possible tokenizations. This observation is demonstrated very helpful in sentence tokenization practice, and is argued to be with far-reaching implications in natural language processing. 1 I n ...

The principle of Per-Survivor Processing (PSP) provides a general framework for the approximation of likelihood-based data detection (search) algorithms whenever the presence of unknown quantities prevents the precise use of the classical Viterbi Algorithm (VA). The PSP concept is based on the realization that decision-directed estimation of the relevant unknown parameters should be embedded in...

■ 2. Section 180. 628 is amended as follows: ■ i. Add alphabetically tolerances for beet, sugar, molasses; berry large shrub/ tree, subgroup 13–07C; berry, low growing, subgroup at 13–07G; onion, bulb, subgroup 3–07A; tea, dried; Ti, leaves; Ti, root; vegetable, leaves of root and tuber, group 2; vegetable, root and tuber, group 1; to the table in paragraph (a); ■ ii. Revise the tolerances for ...

A novel pen-based text entry technique, which yields two characters with one stroke, is introduced, and the results of its investigation are presented. The 2CPS technique is implemented as a gesture-based user interface on a QWERTY soft keyboard. Eight participants completed eight text entry trials on a fully functional version of this stroke-based system on a Pocket PC. The difference between ...

One of the key points addressed by Per Bak in his models of brain function was that biological neural systems must be able not just to learn, but also to adapt—to quickly change their behaviour in response to a changing environment. I discuss this in the context of various simple learning rules and adaptive problems, centred around the Chialvo-Bak ‘minibrain’ model [Neurosci. 90 (1999) 1137–1148].