BibSonomy publications for /author/WeischedelSun Jan 01 00:00:00 CET 2012ACLconf/acl/198732-40An Environment for Acquiring Semantic Information.1987dblp Sun Jan 01 00:00:00 CET 2012ACLconf/acl/198285-88An Improved Heuristic for Ellipsis Processing.1982dblp Fri Dec 23 00:00:00 CET 2011AAAIconf/aaai/1984169-175Living Up To Expectations: Computing Expert Responses.1984dblp Fri Dec 23 00:00:00 CET 2011AAAIconf/aaai/1983424-428Mapping Between Semantic Representations Using Horn Clauses.1983dblp Fri Dec 23 00:00:00 CET 2011ACLconf/acl/1990227-234Multiple Underlying Systems: Translating User Requests into Programs to Produce Answers.1990dblp Fri Dec 23 00:00:00 CET 2011ACLconf/acl/1980If the Parser Fails.1980dblp Fri Dec 23 00:00:00 CET 2011ACLconf/acl/1989193-202A Hybrid Approach to Representation in the Janus Natural Language Processor.1989dblp Fri Dec 23 00:00:00 CET 2011COLINGconf/coling/1984134-138Preventing False Inferences.1984dblp Fri Dec 23 00:00:00 CET 2011COLINGconf/coling/1984101-107Semantic Interpretation Using KL-ONE.1984dblp Fri Dec 23 00:00:00 CET 2011COLINGconf/coling/1984139-143Problem Localization Strategies For Pramatics Processing In Natural-Language Front Ends.1984dblp Mon Dec 05 00:00:00 CET 2011CoRRNymble: a High-Performance Learning Name-findercmp-lg/98030031998dblp Mon Nov 21 00:00:00 CET 2011EMNLPconf/emnlp/20111437-1446Extreme Extraction - Machine Reading in a Week.2011dblp Sat Oct 29 16:36:48 CEST 2011New York, NY, USAProceedings of the 8th international conference on Electronic commerce: The new e-commerce: innovations for conquering current barriers, obstacles and limitations to conducting successful business on the internet463--470ICEC '06Website optimization with web metrics: a case study2006analytics om09 web Web metrics are the measures that reflect how customers are using a website. Companies use these metrics for further improvement of their website. Although most companies today are engaged in website optimization, the actual use of web metrics is a relatively unexplored area. In this paper we address this topic by first reviewing the strengths and weaknesses of the most important source of web metrics (web logs) and then conducting an extensive case study. The literature review revealed a number of serious limitations to the collection and use of web log data. In the case study we interviewed both marketing and IT managers of a major US networking solutions company to explore how they use web metrics for website optimization projects and try to overcome weaknesses.We have found that the various data sources fulfil different purposes: clickstream data enable managers to answer 'when' and 'what' questions, customer surveys 'why' and 'how' questions, and external data to make competitor comparisons. Critical issues involve the lack of industry standards, the volume of data, and the need to supplement clickstream data with qualitative information. Managers highly regard web metrics and are eager to learn how to increase the use of this underutilized data source on online customer behaviour.Sun Sep 18 16:30:37 CEST 2011HLT-NAACLconf/naacl/2006OntoNotes: The 90% Solution.20062006 inventory ontonotes sense senses word Thu Jun 30 00:00:00 CEST 2011Artif. Intell.3225-240An Artificial Intelligence Approach to Language Instruction.101978dblp Mon Jun 27 08:07:51 CEST 2011In Proceedings of DARPA Broadcast News Workshop249--252Performance Measures For Information Extraction19992011 bachelor precision recall While precision and recall have served the information extraction community well as two separate measures of system performance, we show that the F-measure, the weighted harmonic mean of precision and recall, exhibits certain undesirable behaviors. To overcome these limitations, we define an error measure, the slot error rate, which combines the different types of error directly, without having to resort to precision and recall as preliminary measures. The slot error rate is analogous to the word error rate that is used for measuring speech recognition performance; it is intended to be a measure of the cost to the user for the system to make the different types of errors. 1. INTRODUCTION Precision (P) and recall (R) have been used regularly to measure the performance of information retrieval and information extraction systems. Precision deals with substitution and insertion errors while recall deals with substitution and deletion errors. Because of the community's desire to have a si...Tue Jun 21 00:00:00 CEST 2011ANLP194-201Nymble: a High-Performance Learning Name-finder.1997dblp Tue Jun 21 00:00:00 CEST 2011ANLP316-324Named Entity Extraction from Noisy Input: Speech and OCR.2000dblp Tue Jun 21 00:00:00 CEST 2011ANLP226-233A Novel Use of Statistical Parsing to Extract Information from Text.2000dblp Tue Jun 21 00:00:00 CEST 2011ANLP89-92Handling Ill-Formed Input: Session Introduction.1983dblp