%0 Journal Article %1 uzuner05language %A Uzuner, Özlem %A Katz, Boris %D 2005 %J Natural Language Processing – IJCNLP 2005 %K research.nlp cites.ucot research.ir %P 969--980 %T A Comparative Study of Language Models for Book and Author Recognition %U http://dx.doi.org/10.1007/11562214_84 %X Linguistic information can help improve evaluation of similarity between documents; however, the kind of linguistic information to be used depends on the task. In this paper, we show that distributions of syntactic structures capture the way works are written and accurately identify individual books more than 76% of the time. In comparison, baseline features, e.g., tfidf-weighted keywords, function words, etc., give an accuracy of at most 66%. However, testing the same features on authorship attribution shows that distributions of syntactic structures are less successful than function words on this task; syntactic structures vary even among the works of the same author whereas features such as function words are distributed more similarly among the works of an author and can more effectively capture authorship.ER -

@article{uzuner05language, abstract = {Linguistic information can help improve evaluation of similarity between documents; however, the kind of linguistic information to be used depends on the task. In this paper, we show that distributions of syntactic structures capture the way works are written and accurately identify individual books more than 76% of the time. In comparison, baseline features, e.g., tfidf-weighted keywords, function words, etc., give an accuracy of at most 66%. However, testing the same features on authorship attribution shows that distributions of syntactic structures are less successful than function words on this task; syntactic structures vary even among the works of the same author whereas features such as function words are distributed more similarly among the works of an author and can more effectively capture authorship.ER -}, added-at = {2010-10-07T11:05:15.000+0200}, author = {Uzuner, Özlem and Katz, Boris}, biburl = {https://www.bibsonomy.org/bibtex/2bcd9626a85537ba67da3234a8f9c9ebc/msn}, interhash = {fbc674eb44969c6b849befa53b449b7d}, intrahash = {bcd9626a85537ba67da3234a8f9c9ebc}, journal = {Natural Language Processing – IJCNLP 2005}, keywords = {research.nlp cites.ucot research.ir}, pages = {969--980}, timestamp = {2010-10-07T11:05:15.000+0200}, title = {A Comparative Study of Language Models for Book and Author Recognition}, url = {http://dx.doi.org/10.1007/11562214_84}, year = 2005 }