Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics. Brooke, J., Hammond, A., & Hirst, G. Linguistic Issues in Language Technology, 12(2):1--41, 2015. Paper abstract bibtex T. S. Eliot's poem The Waste Land is a notoriously challenging example of modernist poetry, mixing the independent viewpoints of over ten distinct characters without any clear demarcation of which voice is speaking when. In this work, we apply unsupervised techniques in computational stylistics to distinguish the particular styles of these voices, offering a computer's perspective on longstanding debates in literary analysis. Our work includes a model for stylistic segmentation that looks for points of maximum stylistic variation, a k-means clustering model for detecting non-contiguous speech from the same voice, and a stylistic profiling approach which makes use of lexical resources built from a much larger collection of literary texts. Evaluating using an expert interpretation, we show clear progress in distinguishing the voices of The Waste Land as compared to appropriate baselines, and we also offer quantitative evidence both for and against that particular interpretation.
@article{BrookeLiLT,
author = "Julian Brooke and Adam Hammond and Graeme Hirst",
title = "Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics",
year = "2015",
volume = "12",
number = "2",
pages = "1--41",
journal = "Linguistic Issues in Language Technology",
url = "http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/55",
abstract = "T. S. Eliot's poem <I>The Waste Land</I> is a notoriously
challenging example of modernist poetry, mixing the
independent viewpoints of over ten distinct
characters without any clear demarcation of which
voice is speaking when. In this work, we apply
unsupervised techniques in computational stylistics
to distinguish the particular styles of these
voices, offering a computer's perspective on
longstanding debates in literary analysis. Our work
includes a model for stylistic segmentation that
looks for points of maximum stylistic variation, a
k-means clustering model for detecting
non-contiguous speech from the same voice, and a
stylistic profiling approach which makes use of
lexical resources built from a much larger
collection of literary texts. Evaluating using an
expert interpretation, we show clear progress in
distinguishing the voices of <I>The Waste Land</I>
as compared to appropriate baselines, and we also
offer quantitative evidence both for and against
that particular interpretation.",
}
Downloads: 0
{"_id":"rRKKsqnbjZeaCwZcH","bibbaseid":"brooke-hammond-hirst-distinguishingvoicesinithewastelandiusingcomputationalstylistics-2015","downloads":0,"creationDate":"2016-10-19T19:03:54.271Z","title":"Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics","author_short":["Brooke, J.","Hammond, A.","Hirst, G."],"year":2015,"bibtype":"article","biburl":"http://www.cs.toronto.edu/compling/all_bib.bib","bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Julian"],"propositions":[],"lastnames":["Brooke"],"suffixes":[]},{"firstnames":["Adam"],"propositions":[],"lastnames":["Hammond"],"suffixes":[]},{"firstnames":["Graeme"],"propositions":[],"lastnames":["Hirst"],"suffixes":[]}],"title":"Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics","year":"2015","volume":"12","number":"2","pages":"1--41","journal":"Linguistic Issues in Language Technology","url":"http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/55","abstract":"T. S. Eliot's poem <I>The Waste Land</I> is a notoriously challenging example of modernist poetry, mixing the independent viewpoints of over ten distinct characters without any clear demarcation of which voice is speaking when. In this work, we apply unsupervised techniques in computational stylistics to distinguish the particular styles of these voices, offering a computer's perspective on longstanding debates in literary analysis. Our work includes a model for stylistic segmentation that looks for points of maximum stylistic variation, a k-means clustering model for detecting non-contiguous speech from the same voice, and a stylistic profiling approach which makes use of lexical resources built from a much larger collection of literary texts. Evaluating using an expert interpretation, we show clear progress in distinguishing the voices of <I>The Waste Land</I> as compared to appropriate baselines, and we also offer quantitative evidence both for and against that particular interpretation.","bibtex":"@article{BrookeLiLT,\n author = \"Julian Brooke and Adam Hammond and Graeme Hirst\",\n title = \"Distinguishing Voices in <I>The Waste Land</I> using Computational Stylistics\",\n year = \"2015\", \n volume = \"12\", \n number = \"2\", \n pages = \"1--41\",\n journal = \"Linguistic Issues in Language Technology\",\n url = \"http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/55\",\n abstract = \"T. S. Eliot's poem <I>The Waste Land</I> is a notoriously\n challenging example of modernist poetry, mixing the\n independent viewpoints of over ten distinct\n characters without any clear demarcation of which\n voice is speaking when. In this work, we apply\n unsupervised techniques in computational stylistics\n to distinguish the particular styles of these\n voices, offering a computer's perspective on\n longstanding debates in literary analysis. Our work\n includes a model for stylistic segmentation that\n looks for points of maximum stylistic variation, a\n k-means clustering model for detecting\n non-contiguous speech from the same voice, and a\n stylistic profiling approach which makes use of\n lexical resources built from a much larger\n collection of literary texts. Evaluating using an\n expert interpretation, we show clear progress in\n distinguishing the voices of <I>The Waste Land</I>\n as compared to appropriate baselines, and we also\n offer quantitative evidence both for and against\n that particular interpretation.\",\n }\n\n\n\n","author_short":["Brooke, J.","Hammond, A.","Hirst, G."],"key":"BrookeLiLT","id":"BrookeLiLT","bibbaseid":"brooke-hammond-hirst-distinguishingvoicesinithewastelandiusingcomputationalstylistics-2015","role":"author","urls":{"Paper":"http://csli-lilt.stanford.edu/ojs/index.php/LiLT/article/view/55"},"downloads":0},"search_terms":["distinguishing","voices","waste","land","using","computational","stylistics","brooke","hammond","hirst"],"keywords":[],"authorIDs":[],"dataSources":["2vBSdbWEoTEQZtb6g"]}