Over the last two decades, artificial neural networks (ANN) have been applied to solve a variety of problems such as pattern classification and function approximation. In many applications, it is desirable to extract ...
详细信息
Over the last two decades, artificial neural networks (ANN) have been applied to solve a variety of problems such as pattern classification and function approximation. In many applications, it is desirable to extract knowledge from trained neural networks for the users to gain a better understanding of the network's solution. In this paper, we apply REFANN (rule extraction from function approximating neural networks) in dividend events study. Based on our study of 1530 dividend initiations and 692 resumptions events from April 1965 to December 2000, we find that the positive relation between the short-term price reaction and the ratio of annualized dividend amount to stock price is primarily limited to 96 firms that have high dividend ratio and small firm size. The results suggest that the degree of short-term stock price underreaction to dividend events may not be as dramatic as previously believed. The results also show that the relations between the stock price response and firm size is also different across different types of firms. It is suggested that drawing the conclusions from the whole dividend events data may leave some important information unexamined. Our rule extraction method may shed some lights on further empirical research in corporate events studies because more information can be drawn from the data.
We present a variational method for the segmentation of piecewise affine flow fields. Compared to other approaches to motion segmentation, we minimize a single energy functional both with respect to the affine motion ...
详细信息
Optical Character recognition (OCR) systems show poor performance while processing documents like old books or newspapers, Xerox materials, faxed documents, etc. Such documents are considered as degraded documents. On...
详细信息
This paper presents the online handwriting recognition for Indian scripts. The primary concern of the approach is the modeling of human motor functionality while writing characters. This is achieved by looking at the ...
详细信息
Differential methods are frequently used techniques for optic flow computations. They can be classified into local methods such as the Lucas-Kanade technique or Bigün's structure tensor method, and into globa...
详细信息
This paper presents the online handwriting recognition for Indian scripts. The primary concern of the approach is the modeling of human motor functionality while writing characters. This is achieved by looking at the ...
详细信息
ISBN:
(纸本)076951695X
This paper presents the online handwriting recognition for Indian scripts. The primary concern of the approach is the modeling of human motor functionality while writing characters. This is achieved by looking at the whole pen trajectory where the time evaluation of the pen coordinates plays a crucial role. A low complexity classifier was designed and the proposed similarity measure appears to be quite robust against wide variations in writing styles. Initially, the approach was applied for online recognition of handwritten characters in Devnagari and Bangla, the two major Indian scripts. A test on a dataset of considerable size shows promising recognition rates: 97.29% for Devnagari and 96.34% for Bangla.
Polysemy implies the presence of more than one sense of a particular word both in its context-bound and context-free situation. The inherent aspect of polysemy is that a particular word will show multiple sense variat...
详细信息
Polysemy implies the presence of more than one sense of a particular word both in its context-bound and context-free situation. The inherent aspect of polysemy is that a particular word will show multiple sense variations related by way of semantic extension and conceptual expansion. In the last fifty years or so, polysemy has been recognised as one of the central issues in lexical semantics, word sense disambiguation (WSD), actual sense extraction (ASE), language learning, conceptual categorisation of words as well as in computer processing of language. Language users can identify a polysemous word quite easily, but are not equipped to decipher all its possible sense variations without appropriate reference to a proper knowledge-base and other relevant information embedded within contextual environments. We make an empirical effort to understand the basic nature of polysemy in Bangla. We also intend to know how words denote sense variations, which factors are instrumental in making them polysemous, what impact they have on language understanding, and how sense variation can be best understood using information from various sources of knowledge bases. Finally, we use a method to understand the role of various contexts, obtained from corpora, in maintaining an interface between words and their sense variations. Quick reference to local context is handy at times, but reference to focal, topical and global contexts as well as an extralinguistic knowledge base is necessary for understanding sense variation and obtaining actual contextual sense.
This paper deals with the development of a spell-checker in Indian languages using as an example Bangla, the second most popular language on the Indian Subcontinent. A brief review of problems and the current scenario...
详细信息
This paper deals with the development of a spell-checker in Indian languages using as an example Bangla, the second most popular language on the Indian Subcontinent. A brief review of problems and the current scenario of Indian language spell-checkers is described. The approach for the Bangla spell-checker is then elaborated. In this approach the technique works in two stages. The first stage takes care of phonetic similarity error. For that the phonetically similar characters are mapped into single units of character code. A new dictionary D/sub c/ is constructed with this reduced set of alphabets. A phonetically similar but wrongly spelt word can be easily corrected using this dictionary. The second stage takes care of errors other than phonetic similarity. A wrongly spelt word S of n characters is searched in the dictionary D/sub c/. If S is a nonword, its first k/sub 1//spl les/n characters will match with a valid word in D/sub c/. (if k/sub 1/=n then the word in D/sub c/ must be longer than n). A reversed word dictionary D/sub r/ is also generated where the characters of the word are maintained in a reversed order. If the last k/sub 2/ characters of S match with a word in D/sub r/ then, for a single error, it is located within the intersection region of first k/sub 1/+1 and last k/sub 2/+1 characters of S. We observed that this region is very small compared to word length for most cases and the number of suggested correct words can be drastically reduced using this information. We have used our approach in correcting Bangla text, where the problem of inflection is tackled by a simplified version of a morphological analyser. Another problem encountered in Indian languages is the existence of a large number of compound words formed by euphony and assimilation. The problem of compound words is also carefully tackled.
暂无评论