Segmenting documents by stylistic character
Natural Language EngineeringPublished 10 November 2005
N. L. Graham, Graeme Hirst, Bhaskara Marthi
Citations104
SJR quartileQ1
SJR score0.64
SNIP1.66
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The best results, well above baseline, were achieved with time-delay networks that used features related to the author's syntactic preferences, whereas low-level and vocabulary-based features were not found to be useful.
Abstract
As part of a larger project to develop an aid for writers that would help to eliminate stylistic inconsistencies within a document, we experimented with neural networks to find the points in a text at which its stylistic character changes. Our best results, well above baseline, were achieved with time-delay networks that used features related to the author's syntactic preferences, whereas low-level and vocabulary-based features were not found to be useful. An alternative approach with character bigrams was not successful.
Keywords
Computer Science
NatureLearning representations by back-propagating errors
30,885 Citations1986David E. Rumelhart, Geoffrey E. Hinton +1 more
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging
1,531 Citations1995Eric Brill
This paper describes a simple rule-based approach to automated learning of linguistic knowledge that has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance.
Maximum Entropy Model for Part-Of-Speech Tagging
1,276 Citations1996Adwait Ratnaparkhi
A statistical model which trains from a corpus annotated with Part Of Speech tags and assigns them to previously unseen text with state of the art accuracy and discusses the corpus consistency problems discovered during the implementation of these features.
Behavior Research Methods, Instruments, & ComputersMRC psycholinguistic database: Machine-usable dictionary, version 2.00
1,191 Citations1988Michael Wilson
The MRC machine-usable dictionary contains 150,837 words and up 26 linguistic and psycholinguistic attributes from sources that are publicly available but are difficult to obtain and structure into a single dictionary.
Medical Entomology and ZoologyInference and disputed authorship : The Federalist
916 Citations1964Frederick Mosteller, David L. Wallace
Neural NetworksA time-delay neural network architecture for isolated word recognition
587 Citations1990Kevin Lang, Alex Waibel +1 more
A translation-invariant back-propagation network is described that performs better than a sophisticated continuous acoustic parameter hidden Markov model on a noisy, 100-speaker confusable vocabulary isolated word recognition task.
Computational LinguisticsAutomatic Text Categorization in Terms of Genre and Author
401 Citations2000Efstathios Stamatatos, Nikos Fakotakis +1 more
This paper proposes a set of style markers including analysis-level measures that represent the way in which the input text has been analyzed and capture useful stylistic information without additional cost to take full advantage of existing natural language processing (NLP) tools.
Automatic detection of text genre
358 Citations1997Brett Kessler, Geoffrey Numberg +1 more
A theory of genres as bundles of facets, which correlate with various surface cues, are proposed, and it is argued that genre detection based on surface cues is as successful as Detection based on deeper structural properties.
The COCOON platform (University of Paris)An estimate of an upper bound for the entropy of English
354 Citations1992Peter F. Brown, Vincent J. Della Pietra +3 more
An estimate of an upper bound of 1.75 bits for the entropy of characters in printed English is presented by constructing a word trigram model and then computing the cross-entropy between this model and a balanced sample of English text.
Computers and the HumanitiesNeural network applications in stylometry: The Federalist Papers
208 Citations1996Fiona J. Tweedie, Sameer Singh +1 more
It is believed that statistical methods of attributing authorship can be coupled effectively with neural networks to produce a very powerful classification tool.
arXiv (Cornell University)Automatic Detection of Text Genre
206 Citations1997Brett Kessler, Geoffrey Nunberg +1 more
Handbook of Neural Computation
202 Citations2010
The Handbook of Neural Computation is intended to become the standard reference resource for the neural network community, with regularly published supplements keeping readers abreast of late-breaking developments and new advances in this rapidly developing field.
Attributing authorship an introduction
183 Citations2002Harold Love
Detecting Text Similarity over Short Passages: Exploring Linguistic Feature Combinations via Machine Learning
178 Citations1999Vasileios Hatzivassiloglou, Judith L. Klavans +1 more
A new composite similarity metric is presented that combines information from multiple linguistic indicators to measure semantic distance between pairs of small textual units and is evaluated against standard information retrieval techniques, establishing that the new method is more effective in identifying closely related textual units.
How People Write Together
161 Citations1992Ilona Posner, Ronald M. Baecker
A taxonomy of joint writing based on an analysis of interviews with authors who have written documents together is presented, which describes joint writing in terms of four components: roles played in the collaboration, activities performed in the writing process, document control methods used, and writing strategies employed.
Language independent authorship attribution using character level language models
155 Citations2003Fuchun Peng, Dale Schuurmans +2 more
Language and task independent text categorization with simple language models
112 Citations2003Fuchun Peng, Dale Schuurmans +1 more
This work presents a simple method for language independent and task independent text categorization learning, based on character-level n-gram language models, which achieves effective performance across a variety of languages and tasks without requiring feature selection or extensive pre-processing.
Improving data driven wordclass tagging by system combination
100 Citations1998Hans van Halteren, Jakub Zavrel +1 more
How the differences in modelling between different data driven systems performing the same NLP task can be exploited to yield a higher accuracy than the best individual system is examined.
Automatic authorship attribution
91 Citations1999Efstathios Stamatatos, Nikos Fakotakis +1 more
The proposed set of style markers is able to distinguish texts of various authors of a weekly newspaper using multiple regression and is easily trainable and fully-automated requiring no manual text preprocessing nor sampling.
Information Processing & ManagementDiscrimination of authorship using visualization
75 Citations1994Bradley Kjell, Walt Woods +1 more
Visualization techniques help organize the vast amount of data generated in computational studies of literary style by showing two-dimensional representations of the style of the authors of The Federalist Papers.
Computers and the HumanitiesDetecting Collaborations in Text Comparing the Authors' Rhetorical Language Choices in The Federalist Papers
45 Citations2003Jeff Collins, David S. Kaufer +3 more
An attribution study is presented that characterizes the texts according to the representationallanguage choices of the authors, similar to a way close human readers come to know a text and distinguish its rhetorical purpose.
Detecting Stylistic Inconsistencies in Collaborative Writing
43 Citations1996A. Glover, Graeme Hirst
When two or more writers collaborate on a document by each contributing pieces of text, the problem can arise that, while each might be an exemplary piece of writing, they do not cohere into a document that speaks with a single voice.
Visualization of literary style
11 Citations2003Bradley Kjell, Ophir Frieder
Visualization techniques help organize the vast amount of data generated in computational studies of literary style by showing two-dimensional representations of the style of the authors of the Federalist Papers.
Belarusian State Pedagogical University repository (Belarusian State Pedagogical University)Automatic detection of authorship changes within single documents
3 Citations2000N. L. Graham