14 Hits in 4.0 sec

Optimizing term vectors for efficient and robust filtering

David A. Evans, Jeffrey Bennett, David A. Hull
2003 Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval - SIGIR '03  
Results on TREC-2002 filtering-task datasets demonstrate substantial improvements over TREC-median results and rival both idealized IR-based results and optimized (and expensive) SVM-based classifiers  ...  IRIT at TREC '2002: filtering track. Text Retrieval Conference(TREC-2002) ConferenceNotebook, 2002, 413-422. [2] Boughanem, M., Chrisment, C., Tmar, M.  ...  Mercure and MercureFiltre applied for web and filtering tasks at TREC-10. The Tenth Text Retrieval Conference(TREC-2001(TREC- ), 2002 Figure 1 . 1 Term-extraction formulae collection.  ... 
doi:10.1145/860435.860546 dblp:conf/sigir/EvansBH03 fatcat:w6vozwag55bdnkggo2mqqq3mwm

INEX Tweet Contextualization task: Evaluation, results and lesson learned

Patrice Bellot, Véronique Moriceau, Josiane Mothe, Eric SanJuan, Xavier Tannier
2016 Information Processing & Management  
This motivated the proposal of a new track at CLEF INEX lab of Tweet Contextualization.  ...  In the past, the purpose of the TREC Entity Track was to perform entity-oriented searches in the Web [6] .  ...  In 2012, TREC Knowledge Base Acceleration Track 6 started. It aims at filtering a document stream to extract the relevant documents to a set of entities.  ... 
doi:10.1016/j.ipm.2016.03.002 fatcat:7h64buwylvhefbcarhxeusjd5q

Evaluating document filtering systems over time

Tom Kenter, Krisztian Balog, Maarten de Rijke
2015 Information Processing & Management  
We re-evaluate the runs submitted to the Cumulative Citation Recommendation task of the 2012 and 2013 editions of the TREC Knowledge Base Acceleration track, and show that important new insights emerge  ...  In short, the performance is calculated for batches, a trend line is fitted to the results, and the estimated performance of systems at the end of the evaluation period is used to compare systems.  ...  The score used in the last year the track ran is presented in Robertson and Soboroff (2002) as T11U ¼ 2TP À FP.  ... 
doi:10.1016/j.ipm.2015.03.005 fatcat:luykqbq27vdjtpt65ohwm3sp2q

Using language models to improve opinion detection

Faiza Belbachir, Mohand Boughanem
2018 Information Processing & Management  
With the huge volume of opinionated data available on the Web, approaches must be developed to differentiate opinion from fact.  ...  Using the best models, our approach improves on the best baseline of TREC Blog (baseline4) by 30%.  ...  Acknowledgement All this work has been done at the IRIT Laboratory.  ... 
doi:10.1016/j.ipm.2018.07.001 fatcat:qwumrzbywjbolmbfvejwdceneu

Overview of INEX 2013 [chapter]

Patrice Bellot, Antoine Doucet, Shlomo Geva, Sairam Gurajada, Jaap Kamps, Gabriella Kazai, Marijn Koolen, Arunav Mishra, Véronique Moriceau, Josiane Mothe, Michael Preminger, Eric SanJuan (+5 others)
2013 Lecture Notes in Computer Science  
structured or semantic data (Linked Data track); and focused retrieval (Snippet Retrieval and Tweet Contextualization tracks).  ...  This paper gives an overview of all the INEX 2013 tracks, their aims and task, the built test-collections, and gives an initial analysis of the results.  ...  Our goal is to bring together different communities and to foster research at the intersection of Information Retrieval, Databases, and the Semantic Web.  ... 
doi:10.1007/978-3-642-40802-1_27 fatcat:poxx52dr3vgfpcndlticjsl3da

Fusing different information retrieval systems according to query-topics: a study based on correlation in information retrieval systems and TREC topics

Anthony Bigot, Claude Chrisment, Taoufiq Dkaki, Gilles Hubert, Josiane Mothe
2011 Information retrieval (Boston)  
We show that this method is effective when using the TREC ad hoc collection.  ...  We consider the system profile based on the similarity of the set of TREC topics on which systems achieve similar levels of performance.  ...  Clustering queries has also been studied in the web context (Wen et al., 2002) , but based on query logs, which is a different issue.  ... 
doi:10.1007/s10791-011-9169-5 fatcat:muxjiirwbfc63o4ildvlx3zmwu

The INEX Evaluation Initiative [chapter]

Gabriella Kazai, Norbert Gövert, Mounia Lalmas, Norbert Fuhr
2003 Lecture Notes in Computer Science  
One of the largest evaluation initiatives is the Text REtrieval Conference (TREC) 5 , which every year since 1992, runs numerous tracks based on an increasingly diverse set of tasks that are to be performed  ...  The Initiative for the Evaluation of XML Retrieval (INEX) was set up at the beginning of 2002 with the aim to establish an infrastructure and provide means, in the form of a large XML test collection and  ...  Within content-oriented XML retrieval it is aimed at retrieving document components which are specific with regard to the user's information need and exhaustive at the same time. evaluation metric Mathematical  ... 
doi:10.1007/978-3-540-45194-5_19 fatcat:6mqghyeuy5b7tohvob5wjbl7ge

A machine learning approach to sentiment analysis in multilingual Web texts

Erik Boiy, Marie-Francine Moens
2008 Information retrieval (Boston)  
In this paper we present our machine learning experiments with regard to sentiment analysis in blog, review and forum texts found on the World Wide Web and written in English, Dutch and French.  ...  In an alternative approach to negation (Pang et al. 2002) , each word following a negation until the first punctuation receives a tag indicating negation to the learning algorithm.  ...  We are especially very grateful to Didier Bourigault (IRIT, France) for the parsing of the French sentences and to Tem Bertels who collected the French corpus and helped with the annotation of its sentences  ... 
doi:10.1007/s10791-008-9070-z fatcat:ez6qh5lpjfayxoiwjw2pkjzmr4

EMBnet.journal 18 Suppl. B

EMBnet Journal
2012 EMBnet journal  
Segagni et al, presented at the DILS 2012 conference in Washington DC.  ...  Voorhees E (2001) Overview of the QA Track. In Proceedings of the TREC-10 Conference. NIST, Gaithersburg. 2001:157-165. 16.  ...  ProphNet is available as a web application at  ... 
doi:10.14806/ej.18.b.592 fatcat:wlwsmbdlfzbjtk7vyhiabdov6q

Shallow features as indicators of English–German contrasts in lexical cohesion

Kerstin Kunz, Ekaterina Lapshinova-Koltunski, José Manuel Martínez Martínez, Katrin Menzel, Erich Steiner
2017 Languages in Contrast: International Journal for Contrastive Linguistics  
We avoided the distinction, at the syntactic level, between Complement and Adjunct.  ...  References The semantic web: The roles of XML and RDF. Internet Computing, IEEE, 4(5): 63-73. Ferrucci, D. and Lally, A. (2004).  ...  ( 1 means that the relation is also defined in TAC KBP slot filling task; 2 in TREC-08 QA task; 3 in TREC 2002 QA task, i.e. annotation scheme proposed by (Li and Roth, 2002) ; and 4 in LIRICS semantic  ... 
doi:10.1075/lic.16005.kun fatcat:p7pa2crm6rgkrfmsdf7m5265ea

Ontology Population and Concept Search across Ontologies: Challenges and Methodologies

Chetana Gavankar
Semantic Web has brought a new paradigm to web search. The primary components of the Semantic Web, ontologies and knowledge graphs (populated ontologies), are rich sources of domain knowledge.  ...  Identifying the right concepts is a critical part of search-improvement techniques such as web page annotation, query intent capture, and web page classification.  ...  We performed an evaluation on 102 queries that were obtained from two years of TREC web track competitions 6 . This TREC dataset does not contain singletoken queries.  ... 
doi:10.4225/03/59474f646c296 fatcat:obzcfr65znbw7i7dnhu7kabef4

Salience Estimation and Faithful Generation: Modeling Methods for Text Summarization and Generation

Christopher Kedzie
At a high level, we divide these tasks into two categories: content selection, or "what to say" and content realization, or "how to say it" (McKeown, 1985).  ...  Streaming or temporal summarization was first explored in the context of topic detection and tracking and more recently at the Text Retrieval Conference (TREC) (Aslam et al., 2013) .  ...  TREC 2015 Experiments and Results There were three tasks at the TREC 2015 Temporal Summarization shared-task evaluation 2.  ... 
doi:10.7916/d8-61n8-mg23 fatcat:sztaye4ftvhubjibjd3ty5dqy4

CENTRIC 2011 Committee CENTRIC Advisory Chairs CENTRIC 2011 Technical Program Committee

Mario Hoffmann, Guadalupe Ortiz, Gottfried Zimmermann, Eberhard Karls, Rainer Falk, Siemens Ag -München, Juong-Sik Deutschland, Lee, Vitaly Klyuev, Mario Hoffmann, Guadalupe Ortiz, Gottfried Zimmermann (+68 others)
2011 unpublished
II TREC WEB 2009 DIVERSITY TASK RESULTSFor the diversity task, we retained the following runs:• uwgym: this run acts as a baseline run for the track.  ...  For this experiment, we consider the best run submitted by the four best competitors at the TREC Web 2009 adhoc task. Their scores are presented in Table I . [24] .  ... 

Simpozion Ştiinţific Internaţional al Tinerilor Cercetători, Ediţia a 19-a, (16-17 aprilie 2021) : Lucrări ştiinţifice. Volumul 3 [article]

Belostecinic, Grigore (red.)
2021 Zenodo  
work and at home […] .  ...  În cel din urmă caz, agenții de publicitate utilizează fiecare ocazie pentru a atrage atenția, încălcând cu îndrăzneală linia dintre "iritant" și "ofensator".  ...  Majoritatea afacerilor își emit acțiunile și trec procedura de IPO în New York la bursele NYSE și NASDAQ.  ... 
doi:10.5281/zenodo.5669932 fatcat:hwyzmm53mnbvfoogqvhplw7y5i