Using common hypertext links to identify the best phrasal description of target web documents

@misc{citeulike:210428, abstract = {This paper describes previous work which studied and compared the distribution of words in web documents with the distribution of words in \"normal\" flat texts. Based on the findings from this study it is suggested that the traditional IR techniques cannot be used for web search purposes the same way they are used for \"normal\" text collections, e.g. news articles. Then, based on these same findings, I will describe a new document description model which exploits valuable anchor text information...}, author = {Amitay, E. }, citeulike-article-id = {210428}, keywords = {information-extraction, keyphrase-extraction, natural-language-processing, summarization, text}, posted-at = {2005-05-25 15:43:06}, priority = {5}, title = {Using common hypertext links to identify the best phrasal description of target web documents}, url = {http://citeseer.ist.psu.edu/amitay98using.html}, year = {1998} }

TY - GEN ID - citeulike:210428 L3 - citeulike-article-id:210428 TI - Using common hypertext links to identify the best phrasal description of target web documents N2 - This paper describes previous work which studied and compared the distribution of words in web documents with the distribution of words in "normal" flat texts. Based on the findings from this study it is suggested that the traditional IR techniques cannot be used for web search purposes the same way they are used for "normal" text collections, e.g. news articles. Then, based on these same findings, I will describe a new document description model which exploits valuable anchor text information... KW - information-extraction KW - keyphrase-extraction KW - natural-language-processing KW - summarization KW - text AU - Amitay, E PY - 1998/// UR - http://citeseer.ist.psu.edu/amitay98using.html ER -