90,070 Hits in 4.5 sec

Developing an automatic linguistic truncation operator for best-match retrieval of Finnish in inflected word form text database indexes

Kimmo Kettunen
2006 Journal of information science  
Use of inflectional stems has earlier been shown to be a good retrieval method in inflected indexes in a best-match environment for a highly inflected and compound-rich language, Finnish.  ...  In this paper the earlier stem method is elaborated by enhancing the stems with regular expressions.  ...  Developing an automatic linguistic truncation operator for best-match retrieval in inflected word form text database indexes The terms lemmatizer, stemming, inflectional stem generator and enhanced inflectional  ... 
doi:10.1177/0165551506066057 fatcat:62e4v7mt3zbxhetw4i42tus23q

SF-CNN: Deep Text Classification and Retrieval for Text Documents

R. Sarasu, K. K. Thyagharajan, N. R. Shanker
2023 Intelligent Automation and Soft Computing  
correct text documents.  ...  The traditional algorithm performs less because it never considers words' polysemy and the relationship between bag-of-words in keywords.  ...  Customized learning content and storing the content in the databases in a hierarchical structure is disclosed to retrieve documents [2] .  ... 
doi:10.32604/iasc.2023.027429 fatcat:r2czwj5p6jdntkr3lgkp23erma

A Review on WordNet and Vector Space Analysis for Short-text Semantic Similarity

2017 International Journal of Innovations in Engineering and Technology  
The assessment of semantic similarity between the words of a short text is one of the challenging task knowledge based tasks and the tasks in NLP like text summarization, information retrieval, search,  ...  categorization of text and machine learning etc. which uses the sentence similarity measures for assessing the similarity between the short-text or sentences.  ...  the short text because they do not work well in case of short text.  ... 
doi:10.21172/ijiet.81.018 fatcat:7fdugo52c5gonp4e7nmho6kdcq

Electronic Reference Systems in the Year 2000: The Symposium on Advanced Information Processing and Analysis, March 24 - 26, 1992

Lee A. Gladwin
1992 IASSIST Quarterly  
Electronic Reference Systems in the Year 2000: The Symposium on Advanced Information Processing and Analysis, March 24 - 26, 1992  ...  Natural Language Inc. developed a frontend for ORACLE which takes short phrases and even sen-lASSIST Quarterly tences, parses them into SQL statements, and runs them against the database.  ...  Natural Language/Text Processing Papers presented in this session addressed the needs to translate text from foreign languages and then extract information and present it to the user in a meaningful manner  ... 
doi:10.29173/iq437 fatcat:2skgmajievfefglahwxuf3lfpa

Using Oracle® for natural language document retrieval an automatic query reformulation approach

Jens Grivolla
2005 Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '05  
In corporate applications, vast amounts of data are often stored in database systems such as Oracle.  ...  Oracle includes means to deal with full text document retrieval (called Oracle Text) that offer special query operators for searches inside text fields.  ...  Oracle addresses this issue by including full text retrieval methods in their database product.  ... 
doi:10.1145/1076034.1076150 dblp:conf/sigir/Grivolla05 fatcat:335jslxm2bg2zge7qkushzf4xa

Enhancing keyword-based botanical information retrieval with information extraction

Xiaoya Tang
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
Such an approach does not allow matching based on the specific plant characteristic descriptions that are often used in botanical text retrieval.  ...  The results indicate that this approach enhances task-based retrieval performance.  ...  In this study, information techniques are used to enhance keyword-based retrieval by automatically extracting plant characteristic information from texts and allowing users to search with both extracted  ... 
doi:10.1145/1390334.1390505 dblp:conf/sigir/Tang08 fatcat:qnverpkc6fcfbjx7432f4wyj7e

Demonstrating a service-enhanced retrieval system

Philipp Schaer, Philipp Mayr, Peter Mutschke
2010 Proceedings of the American Society for Information Science and Technology  
This paper is a short description of an information retrieval system enhanced by three model driven retrieval services: (1) co-word analysis based query expansion, re-ranking via (2) Bradfordizing and  ...  Each service can be interactively combined with each other to allow an iterative retrieval refinement.  ...  SERVICES FOR RETRIEVAL ENHANCEMENT All proposed models are implemented in a live information system using (1) the Solr search engine, (2) Grails Web framework and (3) Recommind Mindserver to demonstrate  ... 
doi:10.1002/meet.14504701395 fatcat:f2dfwpomcvbfrisyg5j7vemw44

Retrieval effectiveness of tagging systems

Isabella Peters, Laura Schumann, Jens Terliesner, Wolfgang G. Stock
2011 Proceedings of the American Society for Information Science and Technology  
Moreover, several experimental tag-based databases (i.e., power tags, Luhn-tags) have been tested regarding their retrieval effectiveness.  ...  A TREC-like retrieval test was conducted with tags and resources from the social bookmarking system delicious, which resulted in recall and precision values for tag-only searches.  ...  Adjustment of the tag separation algorithm may also enhance precision values of short queries.  ... 
doi:10.1002/meet.2011.14504801338 fatcat:msrnwqcla5aplj6xy32yqvdj7q

State Of The Art In Translation Memory Technology [chapter]

Uwe Reinke
2018 Zenodo  
After taking a closer look at data exchange standards relevant to tm environments, the focus of the paper then shifts towards approaches to enhance the retrieval performance of tm systems looking at both  ...  The paper will start with a short overview of the history of tm systems and a description of their main components and types.  ...  , perhaps to translate the missing areas in texts retrieved from the text memory.  ... 
doi:10.5281/zenodo.1291929 fatcat:t2elaga5ozb7fiu6w3oknohscq

Challenging research issues in data mining, databases and information retrieval

Aparna S. Varde
2009 SIGKDD Explorations  
Data mining research along with related fields such as databases and information retrieval poses challenging problems, especially for doctoral students.  ...  The research spreads over a variety of topics such as text mining, semantic web, multilingual information analysis, heterogeneous data management, database learning, digital libraries and more.  ...  Therefore, it encompasses challenging doctoral research issues in the areas of data mining, databases and information retrieval today that would be of interest to a fairly broad audience in industry and  ... 
doi:10.1145/1656274.1656284 fatcat:kzoqwum75negbldpynaq4zxmfm

BJUT at TREC 2016: Real-Time Summarization Track

Kai Wang, Zhen Yang
2016 Text Retrieval Conference  
External information extracted from Google search engine was well incorporated to enhance the understanding of a users interest.  ...  In Task A, we applied the classifiers to categorize all of the input tweets.  ...  Semantic expansion methods can be leveraged to enhance the retrieval performance.  ... 
dblp:conf/trec/WangY16 fatcat:wtvezixikrezljx3p2rckwio6i

Using NLP for Enhancing Second Language Acquisition

Leonardo Zilio, Rodrigo Wilkens, Cédrick Fairon
2017 RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning  
This study presents SMILLE, a system that draws on the Noticing Hypothesis and on input enhancements, addressing the lack of salience of grammatical information in online documents chosen by a given user  ...  The system can enhance a total of 107 fine-grained types of grammatical structures that are based on the CEFR. An evaluation of some of those structures resulted in an overall precision of 87%.  ...  used in the FLAIR system for retrieving grammatical information from web-based texts.  ... 
doi:10.26615/978-954-452-049-6_107 dblp:conf/ranlp/ZilioWF17 fatcat:ci7ax7lrvrgnvg7txjll7oxcoa

Large Scale Multimedia Management: A Comprehensive Review

Saïd Mahmoudi, Mohammed Amin Belarbi
2022 Information  
This editorial paper discusses the mains challenges of multimedia retrieval in a context of large databases.  ...  Many methods have been developed in the literature to achieve fast and efficient navigating in large databases by using the famous content-based image retrieval (CBIR) methods associated with these methods  ...  They also apply a late fusion process to enhance retrieval precision.  ... 
doi:10.3390/info13010028 fatcat:okdnlufv75bgpdnuiph6k22k2u

The Indexing and Retrieval of Document Images: A Survey

David Doermann
1998 Computer Vision and Image Understanding  
We briefly discuss traditional text indexing techniques on imperfect data and the retrieval of partially converted documents.  ...  This is followed by a more comprehensive review of techniques for the direct characterization, manipulation, and retrieval, of images of documents containing text, graphics, and scene images.  ...  on the enhancement of OCR'd text for IR.  ... 
doi:10.1006/cviu.1998.0692 fatcat:xxl2ynzjkjbeddk2xwkds2g3jq

Tractor: A framework for soft information fusion

M Prentice, M Kandefer, S C Shapiro
2010 2010 13th International Conference on Information Fusion  
The framework utilizes artificial intelligence techniques from natural language understanding, knowledge representation, and information retrieval.  ...  This database is also being used to construct the ontological knowledge base used in the contextual enhancement process. A particular name can be associated with multiple entities.  ...  In order to bring natural language text into a searchable database, these named entity references need to be resolved into either: (a) the unique entity to which it refers or (b) a set of possible referents  ... 
doi:10.1109/icif.2010.5711896 fatcat:q5gdbw7szbbffhqn3pcu7mbx5e
« Previous Showing results 1 — 15 out of 90,070 results