26,582 Hits in 4.4 sec

Matching product titles using web-based enrichment

Vishrawas Gopalakrishnan, Suresh Parthasarathy Iyengar, Amit Madaan, Rajeev Rastogi, Srinivasan Sengamedu
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In this paper, we propose a novel unsupervised matching algorithm that leverages web search engines to (1) enrich product titles by adding important missing tokens that occur frequently in search results  ...  , and (2) compute importance scores for tokens based on their ability to retrieve other (enriched title) tokens in search results.  ...  As can be seen from the figure, our EN+IMP matching scheme with web-based enrichments and importance scores outperforms IDF-based matching.  ... 
doi:10.1145/2396761.2396839 dblp:conf/cikm/GopalakrishnanIMRS12 fatcat:xbnn2hpruvcgvoix5uoq2ayjnu

Matching titles with cross title web-search enrichment and community detection

Nikhil Londhe, Vishrawas Gopalakrishnan, Aidong Zhang, Hung Q. Ngo, Rohini Srihari
2014 Proceedings of the VLDB Endowment  
The first component uses Web searches to "enrich" the given pair of titles: making titles that refer to the same physical entity more similar, and those which do not, much less similar.  ...  There are manifestations of this problem in a variety of domains, such as product or bibliography matching, and location or person disambiguation.  ...  There is another practical reason why product title matching is an important problem on its own -in UK alone, Web searches on this sector constitute a significant portion of Web traffic: as high as 6.06%  ... 
doi:10.14778/2732977.2732990 fatcat:ne75tc3rjnd7heeryb3cwnidf4

A machine learning approach for product matching and categorization

Petar Ristoski, Petar Petrovski, Peter Mika, Heiko Paulheim, Claudia d'Amato
2018 Semantic Web Journal  
To improve the consumer experience, approaches for product integration on the Web are needed.  ...  boost the performance of the feature extraction model, thus leading to better product matching and categorization performances.  ...  The approach first enriches the offer's title with tokens using web search engine.  ... 
doi:10.3233/sw-180300 fatcat:vf44he52vbdm7hvigq3faqs6wm

Table Enrichment System for Machine Learning [article]

Yuyang Dong, Masafumi Oyamada
2022 arXiv   pre-print
We demonstrate our system with a web UI to show the use cases of table enrichment.  ...  We propose a table enrichment system that enriches a query table by adding external attributes (columns) from data lakes and improves the accuracy of machine learning predictive models.  ...  The purpose of using a text-based query is to match a related table in accordance with the description of the ML task.  ... 
arXiv:2204.08235v1 fatcat:lj5ei7rus5cujpghib45idw55u

Enriching Product Ads with Metadata from HTML Annotations [chapter]

Petar Ristoski, Peter Mika
2016 Lecture Notes in Computer Science  
We use these features to identify matching products across different online shops and enrich product ads with the extracted data.  ...  Our evaluation on three product categories related to electronics show promising results in terms of enriching product ads with useful product data.  ...  We would also like to acknowledge the support, help and insights of the Yahoo Gemini Product Ads engineering and the Yahoo Labs Advertising Sciences teams, in particular Nagaraj Kota and Ben Shahshahani  ... 
doi:10.1007/978-3-319-34129-3_10 fatcat:ojhfttlz7jfrbf7x2rc6lyttxa

From relevance to intelligence

Wei-Ying Ma
2005 Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval - MIR '05  
Has Many Other Rich Structures Wei-Ying Ma, Microsoft Research Asia Using Block-level PageRank to Improve Search Vision-based Approach for Web Object Extraction • The Problem • Our Solution based on Extended  ...  The International Atomic Energy Agency has concluded that Iran has secretly produced small amounts of nuclear materials including low enriched uranium and plutonium that could be used to develop nuclear  ... 
doi:10.1145/1101826.1101827 dblp:conf/mir/Ma05 fatcat:ezgdvrytlzg2zmrjx2opvy5t6m

An aspect-driven method for enriching product catalogs with user opinions

Tiago de Melo, Altigran da Silva, Edleno S. de Moura
2018 Journal of the Brazilian Computer Society  
This is done by matching aspect expression identified in opinions with attributes from the product, which we model here as aspect classes.  ...  In this paper, we propose a method for enriching product catalogs, which traditionally include only objective data provided by manufacturers or retailers, with subjective information extracted from reviews  ...  Availability of data and materials The datasets used in experiments of this article are available at webpage:  ... 
doi:10.1186/s13173-018-0080-4 fatcat:sgpebsd3lzf35glpgxil3h5pyq

Linking FRBR Entities to LOD through Semantic Matching [chapter]

Naimdjon Takhirov, Fabien Duchateau, Trond Aalberg
2011 Lecture Notes in Computer Science  
The main contribution is a basis for semantic enrichment and verication of works identied in existing metadata.  ...  Specialized knowledge bases already use this mechanism to automatically create entities for a generic knowledge base, often with incomplete information. The last benet is the semantic enrichment.  ...  Experiments In our experiments, a list of the 80 best selling ction authors from Wikipedia 5 was used to query for product descriptions on Amazon bookstore (using the Amazon Product Advertising API 6 )  ... 
doi:10.1007/978-3-642-24469-8_30 fatcat:wjn7jz5pknb35kicr4f2avbxoe

A New Approach to Information Extraction in User-Centric E-Recruitment Systems

Malik Nabeel Ahmed Awan, Sharifullah Khan, Khalid Latif, Asad Masood Khattak
2019 Applied Sciences  
The extracted information entities are enriched with knowledge using Linked Open Data.  ...  Furthermore, job context information is expanded using a job description domain ontology based on the contextual and knowledge information.  ...  The enriched and context-aware information is stored in the knowledge base built using Linked Open Data principles.  ... 
doi:10.3390/app9142852 fatcat:sy62dzuvcra7zfi44xm64ytwom

The WDC Gold Standards for Product Feature Extraction and Product Matching [chapter]

Petar Petrovski, Anna Primpeli, Robert Meusel, Christian Bizer
2017 Lecture Notes in Business Information Processing  
Determining whether two offers refer to the same product involves extracting a set of features (product attributes) from the web pages containing the offers and comparing these features using a matching  ...  The WDC Product Matching Gold Standard consists of over 75 000 correspondences between 150 products (mobile phones, TVs, and headphones) in a central catalog and offers for these products on the 32 web  ...  In [1] the authors introduce a novel approach for product matching by enriching product titles with essential missing tokens and calculate the importance score computation that takes context into account  ... 
doi:10.1007/978-3-319-53676-7_6 fatcat:dttuf3kqxrcvnbodqbb5teuiii

Automatic metadata enrichment in news production

E. Mannens, R. Troncy, K. Braeckman, D. Van Deursen, W. Van Lancker, R. De Sutter, R. Van de Walle
2009 2009 10th Workshop on Image Analysis for Multimedia Interactive Services  
In this paper, we show how personalized distribution and consumption of news items can be enabled by automatically enriching news metadata with open linked datasets available on the Web of data, thus providing  ...  News production is characterized by complex and dynamic workflows in which it is important to produce and distribute news items as fast as possible.  ...  The web-based user interface uses Google's Web Toolkit and connects to a SPARQL endpoint where all RDF metadata of the news items is stored.  ... 
doi:10.1109/wiamis.2009.5031432 dblp:conf/wiamis/MannensTBDLSW09 fatcat:kjun6wirwzghpnooe2iz55gxkq

Semantic Similarity Strategies for Job Title Classification [article]

Yun Zhu, Faizan Javed, Ozgur Ozturk
2016 arXiv   pre-print
These applications can range from faceted browsing of items to product recommendations and big data analytics.  ...  titles in our taxonomy.  ...  A field-to-field similarity matching approach then matches job ads to job categories.  ... 
arXiv:1609.06268v1 fatcat:weyapdfp2raejl374nfjdjmgpi

Exposing the hidden web for chemical digital libraries

Sascha Tönnies, Benjamin Köhncke, Oliver Koepler, Wolf-Tilo Balke
2010 Proceedings of the 10th annual joint conference on Digital libraries - JCDL '10  
To use our framework thus promises to expose a large part of the currently still hidden chemical Web, making the techniques employed interesting for chemical information providers like digital libraries  ...  In this paper we present a framework for automatically generating metadata-enriched index pages for all documents in a given chemical collection.  ...  Figure 6 . 6 Retrieved documents per query: enriched versus structure search Therefore, our chemist first tries a keyword-based Web search using the query term 'methoxybenzene', specifically on information  ... 
doi:10.1145/1816123.1816159 dblp:conf/jcdl/TonniesKKB10 fatcat:dgdy5pfgjvhuheo5nhalxepjji

An Efficient Method for Tagging a Query with Category Labels Using Wikipedia towards Enhancing Search Engine Results

Milad Alemzadeh, Fakhri Karray
2010 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology  
matching categories or enriching the query itself.  ...  the given query using Wikipedia category hierarchy.  ...  INTRODUCTION The goal of categorizing and enriching a user's query is to improve the query in a way that search tools would be able to return results refined to match the query more precisely.  ... 
doi:10.1109/wi-iat.2010.267 dblp:conf/webi/AlemzadehK10 fatcat:orsp2wtnaneqddtp4ff5f5x4eu


Fabien Duchateau, Naimdjon Takhirov, Trond Aalberg
2011 Proceeding of the 11th annual international ACM/IEEE joint conference on Digital libraries - JCDL '11  
In this demo, we present an approach to transform Web-based resources to a FRBR compatible form, a process known as FRBRization.  ...  However, the amount of information found on the Web is far larger than in digital libraries.  ...  CONCLUSION In this demo, we have presented a tool to transform a Web-based product into the FRBR model.  ... 
doi:10.1145/1998076.1998183 dblp:conf/jcdl/DuchateauTA11 fatcat:7hatlybvdvbl7hhmcwnpdmhnc4
« Previous Showing results 1 — 15 out of 26,582 results