From jelsas+ at cs.cmu.edu Thu May 8 13:46:06 2008 From: jelsas+ at cs.cmu.edu (Jonathan Elsas) Date: Thu, 8 May 2008 13:46:06 -0400 Subject: IR Series - Grace, Hui Yang - Friday May 16th - 12:00 (noon), NSH 3002 Message-ID: Greetings, Please join us for the upcoming IR Series talk! Lunch will be provided by Yahoo! Title: Ontology Learning by Supervised Hierarchical Clustering Who: Grace, Hui Yang When: Friday, May 16th, 12:00pm Where: NSH 3002 Abstract: This work makes novel use of supervised clustering as the basic framework to construct concept ontology interactively or automatically. Supervised hierarchical clustering is used to organize ontology fragments, which are identified by techniques in natural language processing and information retrieval, into hierarchies. At each clustering iteration, a distance metric is learned from the clustering given by either pseudo or real feedback. K-medoids clustering with sampling is then used to group the concepts at the higher level. A web-based cluster naming algorithm is also presented. By conducting a user evaluation, the system is shown to be effective to save human efforts in the interactive runs. Both automatic and interactive runs of the experiments show that the approach is effective. From jelsas+ at cs.cmu.edu Fri May 16 11:29:22 2008 From: jelsas+ at cs.cmu.edu (Jonathan Elsas) Date: Fri, 16 May 2008 11:29:22 -0400 Subject: IR Series - Grace, Hui Yang - Friday May 16th - 12:00 (noon), NSH 3002 In-Reply-To: References: Message-ID: <25C41DFD-954C-4F96-9FB4-6B1D8C6AA7CA@cs.cmu.edu> Reminder: Today at Noon On May 8, 2008, at 1:46 PM, Jonathan Elsas wrote: > Greetings, > > Please join us for the upcoming IR Series talk! > > Lunch will be provided by Yahoo! > > Title: > Ontology Learning by Supervised Hierarchical Clustering > > Who: Grace, Hui Yang > When: Friday, May 16th, 12:00pm > Where: NSH 3002 > > Abstract: > This work makes novel use of supervised clustering as the basic > framework to construct concept ontology interactively or > automatically. Supervised hierarchical clustering is used to > organize ontology fragments, which are identified by techniques in > natural language processing and information retrieval, into > hierarchies. At each clustering iteration, a distance metric is > learned from the clustering given by either pseudo or real > feedback. K-medoids clustering with sampling is then used to group > the concepts at the higher level. A web-based cluster naming > algorithm is also presented. By conducting a user evaluation, the > system is shown to be effective to save human efforts in the > interactive runs. Both automatic and interactive runs of the > experiments show that the approach is effective. > > > From jelsas+ at cs.cmu.edu Mon May 19 09:30:12 2008 From: jelsas+ at cs.cmu.edu (Jonathan Elsas) Date: Mon, 19 May 2008 09:30:12 -0400 Subject: IR Series - Justin Betteridge - Friday, May 23, 2008, 12:00pm, NSH 3002 Message-ID: <8E7070CE-CBD9-4241-854F-CFC8757B8B21@cs.cmu.edu> Hello -- Please join us for another IR Series talk! Lunch will be provided by Yahoo! Who: Justin Betteridge When: Friday, May 23, 2008, 12:00 pm Where: NSH 3002 Title: Linguistic Pattern Learning for Web Information Extraction Abstract: Most approaches to automatically extracting structured information from the web rely on surface text patterns. However, the manner in which such patterns are defined, learned, and employed in the larger system varies with each case. In this talk, I will outline the spectrum of previous work in this area and argue for a linguistically-motivated definition, a hybrid heuristic/ classifier-based assessment, and a multi-purpose employment of textual patterns in the context of Web Information Extraction (WIE). I will also give preliminary results from adopting such an approach in our WIE system. From jelsas+ at cs.cmu.edu Thu May 22 15:52:22 2008 From: jelsas+ at cs.cmu.edu (Jonathan Elsas) Date: Thu, 22 May 2008 15:52:22 -0400 Subject: IR Series - Justin Betteridge - Friday, May 23, 2008, 12:00pm, NSH 3002 In-Reply-To: <8E7070CE-CBD9-4241-854F-CFC8757B8B21@cs.cmu.edu> References: <8E7070CE-CBD9-4241-854F-CFC8757B8B21@cs.cmu.edu> Message-ID: <1586106B-4579-494F-9945-2A47318F7ED8@cs.cmu.edu> Reminder: Justin Betteridge is speaking at the IR series tomorrow, noon, with lunch provided. On May 19, 2008, at 9:30 AM, Jonathan Elsas wrote: > Hello -- > > Please join us for another IR Series talk! > > Lunch will be provided by Yahoo! > > Who: Justin Betteridge > When: Friday, May 23, 2008, 12:00 pm > Where: NSH 3002 > > Title: Linguistic Pattern Learning for Web Information Extraction > > Abstract: > Most approaches to automatically extracting structured information > from the web > rely on surface text patterns. However, the manner in which such > patterns are > defined, learned, and employed in the larger system varies with each > case. In > this talk, I will outline the spectrum of previous work in this area > and argue > for a linguistically-motivated definition, a hybrid heuristic/ > classifier-based > assessment, and a multi-purpose employment of textual patterns in > the context of > Web Information Extraction (WIE). I will also give preliminary > results from > adopting such an approach in our WIE system. > >