In this paper, we describe a system that applies maximum entropy (ME) models to the task of named entity recognition (NER). Starting with an annotated corpus and a set of features which are easily obtainable for almost any language, we first build a baseline NE recognizer which is then used to extract the named entities and their context information from additional nonannotated data. In turn, t...

We have participated in three open tracks of Chinese word segmentation and named entity recognition tasks of SIGHAN Bakeoff3. We take a probabilistic feature based Maximum Entropy (ME) model as our basic frame to combine multiple sources of knowledge. Our named entity recognizer achieved the highest F measure for MSRA, and word segmenter achieved the medium F measure for MSRA. We find effective...

In this paper, we have developed conditions under which the entropy function and the residual entropy function characterize the distribution. We have also studied some stochastic comparisons based on the entropy measure and established relations between entropy comparisons and comparisons with respect to other measures in reliability. Conditions for decreasing (increasing) uncertainty in a resi...

The concept of uncertain entropy is used to provide a quantitative measurement of the uncertainty associated with uncertain variables. After introducing the definition, this paper gives some examples of entropy of uncertain variables. Furthermore this paper proposes the maximum entropy principle for uncertain variables, that is, out of all the uncertainty distributions satisfying given constrai...

Evidence from climate science suggests that a principle of maximum thermodynamic entropy production can be used to make predictions about some physical systems. I discuss the general form of this principle and an inherent problem with it, currently unsolved by theoretical approaches: how to determine which system it should be applied to. I suggest a new way to derive the principle from statisti...

Within the framework of discrete probabilistic uncertain reasoning a large literature exists justifying the maximum entropy inference process, ME, as being optimal in the context of a single agent whose subjective probabilistic knowledge base is consistent. In particular Paris and Vencovská completely characterised the ME inference process by means of an attractive set of axioms which an infere...

Multi-instance data, in which each object (bag) contains a collection of instances, are widespread in machine learning, computer vision, bioinformatics, signal processing, and social sciences. We present a maximum entropy (ME) framework for learning from multi-instance data. In this approach each bag is represented as a distribution using the principle of ME. We introduce the concept of confide...

This paper reports a new reading for wavelets, which is based on the classical ’De Broglie’ principle. The waveparticle duality principle is adapted to wavelets. Every continuous basic wavelet is associated with a proper probability density, allowing defining the Shannon entropy of a wavelet. Further entropy definitions are considered, such as Jumarie or Renyi entropy of wavelets. We proved tha...

in recent years, decrease in depth of uromia lake, has resulted in higher increase of salinity threat in agricultural lands around the lake. the aims of this study were 1- investigation of the spatial changes in soil salinity using the bayesian maximum entropy method (bme); 2- prediction of the boundary between saline and agricultural lands; and 3- assessment of the uncertainty involved with sa...