Style Processing

Classification:

Taxonomy and Evaluation of Markers for Computational Stylistics

Authorship: 
Foaad Khosmood and Robert Levinson
Publication: 
International Conference on Artificial Intelligence 2011

Most machine-learning methods rely on feature extraction to model the text and perform classification. But what are the best features for making style based distinctions? While many researchers have developed particular collections of features – called style markers – no definitive list exists. In this paper we present an organized collection of such style markers with performance data on a diverse set of texts.

Publication Type:

Classification:

502 markers used in ICAI-2011 paper

This is the system output for a typical document where 502 markers were extracted. The number on the left corresponds with the marker # first value on the right, and the subsequent values are one higher each. The markers are listed without statistical parts (like average, median or variance), but in general each marker array is represented by the 5-tuple (maximum, minimum, mean, median and variance.)
The POS-token ratios (#5-13)  are labelled as follows: 

over 4000 marker instances now extractable

Recently we were asked if we truly have over 1000 markers. Actually, at the moment we have over 4000 instances (meaning floating point numbers). This is part of the reason we think a taxonomy is necessary to standardize these markers.

Classification:

Computational Stylistics: Generation, Classification and Transformation

Authorship: 
Foaad Khosmood and Robert Levinson
Publication: 
UCSC Research Review Day 2010

Publication Type:

Classification:

Automatic Synonym and Phrase Replacement Show Promise for Style Transformation

Authorship: 
Foaad Khosmood and Robert Levinson
Publication: 
International Conference on Machine Learning and Applications (ICMLA 2010)

Publication Type:

Classification:

Grapevine: A Gossip Generation System

Authorship: 
Foaad Khosmood and Marilyn Walker
Publication: 
Foundations of Digital Games - 2010

Publication Type:

Classification:

Toward Automated Stylistic Transformation of Natural Language Text

Authorship: 
Khosmood and Levinson
Publication: 
Digital Humanities 2009

Publication Type:

Classification:

AUTOMATIC STYLISTIC PROCESSING FOR CLASSIFICATION AND TRANSFORMATION OF NATURAL LANGUAGE TEXT

Authorship: 
Foaad Khosmood
Publication: 
Thesis proposal

Style is an integral part of natural language in written, spoken, or machine generated forms. Natural language styles are understood, mimicked and transformed by human agents with ease. We believe that like natural language processing (NLP) in general, natural language styles can also be processed, recognized, generated and transformed computationally. In this document, we propose to build a modular, extensible system that automatically performs style-based classification and transformation on written language.

Classification:

Automatic natural language style classification and transformation

Authorship: 
Foaad Khosmood and Robert Levinson
Publication: 
BCS Corpus Profiling Workshop - 2008

Style is an integral part of natural language in written, spoken or machine generated forms. Humans have been dealing with style in language since the beginnings of language itself, but computers and machine processes have only recently begun to process natural language styles. Automatic processing of styles poses two interrelated challenges: classification and transformation.

Publication Type:

Classification:

Pages

Subscribe to Ayandeh RSS