Impact of imperfect OCR on part-of-speech tagging Export

@misc{citeulike:1272757, abstract = {Part-of-speech (POS) tagging is the foundation of natural language processing (NLP) systems, and thus has been an active area of research for many years. However, one question remains unanswered: How will a POS tagger behave when the input text is not error-free? This issue can be of great importance when the text comes from imperfect sources like Optical Character Recognition (OCR). This paper analyzes the performance of both individual POS taggers and combination systems on imperfect text. ...}, author = {Lin, Xiaofan}, citeulike-article-id = {1272757}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.376}, comment = {performance drops linearly with character error-rate}, keywords = {errors, pos-tagging}, posted-at = {2007-05-02 23:23:03}, priority = {2}, title = {Impact of imperfect OCR on part-of-speech tagging}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.376} }

TY - GEN ID - citeulike:1272757 L3 - citeulike-article-id:1272757 N2 - Part-of-speech (POS) tagging is the foundation of natural language processing (NLP) systems, and thus has been an active area of research for many years. However, one question remains unanswered: How will a POS tagger behave when the input text is not error-free? This issue can be of great importance when the text comes from imperfect sources like Optical Character Recognition (OCR). This paper analyzes the performance of both individual POS taggers and combination systems on imperfect text. ... TI - Impact of imperfect OCR on part-of-speech tagging KW - errors KW - pos-tagging N1 - performance drops linearly with character error-rate AU - Lin, Xiaofan UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.376 ER -