Unsupervised stylistic segmentation of poetry with change curves and extrinsic features. Brooke, J., Hammond, A., & Hirst, G. In Proceedings, Workshop on Computational Linguistics for Literature, Montreal, 2012. abstract bibtex The identification of stylistic inconsistency is a challenging task relevant to a number of genres, including literature. In this work, we carry out stylistic segmentation of a well-known poem, The Waste Land by T.S. Eliot, which is traditionally analyzed in terms of numerous voices which appear throughout the text. Our method, adapted from work in topic segmentation and plagiarism detection, predicts breaks based on a curve of stylistic change which combines information from a diverse set of features, most notably co-occurrence in larger corpora via reduced-dimensionality vectors. We show that this extrinsic information is more useful than (within-text) distributional features. We achieve well above baseline performance on both artificial mixed-style texts and The Waste Land itself.
@InProceedings{ brooke8,
author = {Julian Brooke and Adam Hammond and Graeme Hirst},
title = {Unsupervised stylistic segmentation of poetry with change
curves and extrinsic features},
address = {Montreal},
booktitle = {Proceedings, Workshop on Computational Linguistics for
Literature},
year = {2012},
download = {http://ftp.cs.toronto.edu/pub/gh/Brooke-etal-CL+Lit-2012.pdf}
,
abstract = {The identification of stylistic inconsistency is a
challenging task relevant to a number of genres, including
literature. In this work, we carry out stylistic
segmentation of a well-known poem, <I>The Waste Land</I> by
T.S. Eliot, which is traditionally analyzed in terms of
numerous voices which appear throughout the text. Our
method, adapted from work in topic segmentation and
plagiarism detection, predicts breaks based on a curve of
stylistic change which combines information from a diverse
set of features, most notably co-occurrence in larger
corpora via reduced-dimensionality vectors. We show that
this extrinsic information is more useful than
(within-text) distributional features. We achieve well
above baseline performance on both artificial mixed-style
texts and <I>The Waste Land</I> itself.}
}
Downloads: 0
{"_id":{"_str":"53d57a49f414ae191e0003bf"},"__v":0,"authorIDs":[],"author_short":["Brooke, J.","Hammond, A.","Hirst, G."],"bibbaseid":"brooke-hammond-hirst-unsupervisedstylisticsegmentationofpoetrywithchangecurvesandextrinsicfeatures-2012","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Julian"],"propositions":[],"lastnames":["Brooke"],"suffixes":[]},{"firstnames":["Adam"],"propositions":[],"lastnames":["Hammond"],"suffixes":[]},{"firstnames":["Graeme"],"propositions":[],"lastnames":["Hirst"],"suffixes":[]}],"title":"Unsupervised stylistic segmentation of poetry with change curves and extrinsic features","address":"Montreal","booktitle":"Proceedings, Workshop on Computational Linguistics for Literature","year":"2012","download":"http://ftp.cs.toronto.edu/pub/gh/Brooke-etal-CL+Lit-2012.pdf","abstract":"The identification of stylistic inconsistency is a challenging task relevant to a number of genres, including literature. In this work, we carry out stylistic segmentation of a well-known poem, <I>The Waste Land</I> by T.S. Eliot, which is traditionally analyzed in terms of numerous voices which appear throughout the text. Our method, adapted from work in topic segmentation and plagiarism detection, predicts breaks based on a curve of stylistic change which combines information from a diverse set of features, most notably co-occurrence in larger corpora via reduced-dimensionality vectors. We show that this extrinsic information is more useful than (within-text) distributional features. We achieve well above baseline performance on both artificial mixed-style texts and <I>The Waste Land</I> itself.","bibtex":"@InProceedings{\t brooke8,\n author\t= {Julian Brooke and Adam Hammond and Graeme Hirst},\n title\t\t= {Unsupervised stylistic segmentation of poetry with change\n\t\t curves and extrinsic features},\n address\t= {Montreal},\n booktitle\t= {Proceedings, Workshop on Computational Linguistics for\n\t\t Literature},\n year\t\t= {2012},\n download\t= {http://ftp.cs.toronto.edu/pub/gh/Brooke-etal-CL+Lit-2012.pdf}\n\t\t ,\n abstract\t= {The identification of stylistic inconsistency is a\n\t\t challenging task relevant to a number of genres, including\n\t\t literature. In this work, we carry out stylistic\n\t\t segmentation of a well-known poem, <I>The Waste Land</I> by\n\t\t T.S. Eliot, which is traditionally analyzed in terms of\n\t\t numerous voices which appear throughout the text. Our\n\t\t method, adapted from work in topic segmentation and\n\t\t plagiarism detection, predicts breaks based on a curve of\n\t\t stylistic change which combines information from a diverse\n\t\t set of features, most notably co-occurrence in larger\n\t\t corpora via reduced-dimensionality vectors. We show that\n\t\t this extrinsic information is more useful than\n\t\t (within-text) distributional features. We achieve well\n\t\t above baseline performance on both artificial mixed-style\n\t\t texts and <I>The Waste Land</I> itself.}\n}\n\n","author_short":["Brooke, J.","Hammond, A.","Hirst, G."],"key":"brooke8","id":"brooke8","bibbaseid":"brooke-hammond-hirst-unsupervisedstylisticsegmentationofpoetrywithchangecurvesandextrinsicfeatures-2012","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"www.cs.toronto.edu/~fritz/tmp/compling.bib","creationDate":"2014-07-27T22:16:41.208Z","downloads":0,"keywords":[],"search_terms":["unsupervised","stylistic","segmentation","poetry","change","curves","extrinsic","features","brooke","hammond","hirst"],"title":"Unsupervised stylistic segmentation of poetry with change curves and extrinsic features","year":2012,"dataSources":["n8jB5BJxaeSmH6mtR","6b6A9kbkw4CsEGnRX"]}