Filters








3,615 Hits in 7.7 sec

Efficient query processing in distributed search engines

Simon Jonassen
2012 SIGIR Forum  
Our first approach combines the advantage of pipelined and traditional (non-pipelined) query processing.  ...  For the second approach, we follow an alternative direction and look at document-at-a-time processing of sub-queries and skipping.  ...  Rocha-Junior for the useful advices and comments on the paper. Acknowledgments. This work was done while the second author was an intern at Yahoo!  ... 
doi:10.1145/2492189.2492201 fatcat:uwasxhngrfgntemkhawyv3te64

Neural Networks for Information Retrieval

Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
The aim of this full-day tutorial is to give a clear overview of current tried-and-trusted neural methods in IR and how they bene t IR research.  ...  It covers key architectures, as well as the most promising future directions. *  ...  One of the big challenges for IR at the moment is how to process full document text using neural networks.  ... 
doi:10.1145/3077136.3082062 dblp:conf/sigir/KenterBGDRM17 fatcat:yxuiajzjlfaixlnhc6rrsud6ry

Neural Networks for Information Retrieval [article]

Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2017 arXiv   pre-print
The aim of this full-day tutorial is to give a clear overview of current tried-and-trusted neural methods in IR and how they benefit IR research.  ...  It covers key architectures, as well as the most promising future directions.  ...  One of the big challenges for IR at the moment is how to process full document text using neural networks.  ... 
arXiv:1707.04242v1 fatcat:4idscmq26fa5bjupldwuyghq4m

Neural Networks for Information Retrieval

Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
2018 Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining - WSDM '18  
The aim of this full-day tutorial is to give a clear overview of current tried-and-trusted neural methods in IR and how they bene t IR research.  ...  It covers key architectures, as well as the most promising future directions. *  ...  One of the big challenges for IR at the moment is how to process full document text using neural networks.  ... 
doi:10.1145/3159652.3162009 dblp:conf/wsdm/KenterBGDRM18 fatcat:ybdeuuxcbnh2np34k3y4ve5ovu

Text-to-Video: Story Illustration from Online Photo Collections [chapter]

Katharina Schwarz, Pavel Rojtberg, Joachim Caspar, Iryna Gurevych, Michael Goesele, Hendrik P. A. Lensch
2010 Lecture Notes in Computer Science  
We present a first system to semi-automatically create a visual representation for a given, short text.  ...  We then select the final images in a user-assisted process and automatically create a storyboard or photomatic animation. We demonstrate promising initial results on several types of texts.  ...  We would like to thank the Flickr users for the images used in our research.  ... 
doi:10.1007/978-3-642-15384-6_43 fatcat:yvxuapdk6rhwfdrsmzlft7duiu

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval [article]

Luyu Gao, Jamie Callan
2021 arXiv   pre-print
However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full potential.  ...  Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval.  ...  Combining the two, we propose coCondenser pre-training, which unsupervisedly learns a corpus-aware pretrained model for dense retrieval.  ... 
arXiv:2108.05540v1 fatcat:q46xcg6tpnbn7inill6qwiahym

A scalable approach to legal question answering

Zachary Bennett, Tony Russell-Rose, Kate Farmer
2017 Proceedings of the 16th edition of the International Conference on Articial Intelligence and Law - ICAIL '17  
CCS CONCEPTS • Information systems ~Question answering • Information systems ~Search engine architectures and scalability • Information systems ~Information retrieval query processing KEYWORDS Text mining  ...  , question answering, semantic retrieval.  ...  SYSTEM OVERVIEW Lexis Answers uses a large-scale Natural Language Processing (NLP) pipeline for extracting information from relevant sources.  ... 
doi:10.1145/3086512.3086547 dblp:conf/icail/BennettRF17 fatcat:docmpx2fsrbxvksym4hkushkue

Connecting wikis and natural language processing systems

René Witte, Thomas Gitzinger
2007 Proceedings of the 2007 international symposium on Wikis - WikiSym '07  
A system architecture providing the integration is presented, as well as first results from an initial implementation based on the GATE framework for NLP and the MediaWiki system.  ...  We investigate the integration of Wiki systems with automated natural language processing (NLP) techniques.  ...  Acknowledgments Ralf Krestel contributed to the automatic summarization NLP pipelines. Thomas Kappler contributed to the NLP-Wiki upload framework.  ... 
doi:10.1145/1296951.1296969 dblp:conf/wikis/WitteG07 fatcat:yq6ts5bedjglje6zlvpmcavxnq

Big Data Semantics

Paolo Ceravolo, Antonia Azzini, Marco Angelini, Tiziana Catarci, Philippe Cudré-Mauroux, Ernesto Damiani, Alexandra Mazak, Maurice Van Keulen, Mustafa Jarrar, Giuseppe Santucci, Kai-Uwe Sattler, Monica Scannapieco (+3 others)
2018 Journal on Data Semantics  
Big Data technology has discarded traditional data modeling approaches as no longer applicable to distributed data processing.  ...  Indeed, multiple components and procedures must be coordinated to ensure a high level of data quality and accessibility for the application layers, e.g., data analytics and reporting.  ...  Representing Processes The complexity of Big Data architectures has encouraged the definition of work-flow languages for managing pipelines.  ... 
doi:10.1007/s13740-018-0086-2 fatcat:bhbeyntbtzdkvf5t3dcko42jpy

PLAN2L: a web tool for integrated text mining and literature-based bioentity relation extraction

M. Krallinger, C. Rodriguez-Penagos, A. Tendulkar, A. Valencia
2009 Nucleic Acids Research  
Here we present PLAN2L, a web-based online search system that integrates text mining and information extraction techniques to access systematically information useful for analyzing genetic, cellular and  ...  Beyond single entities, also predefined pairs of entities can be provided as queries for which literature-derived relations together with textual evidences are returned.  ...  TECHNICAL DESCRIPTION OF THE TEXT MINING PIPELINE A document retrieval pipeline that takes into account several sources of evidence for the determining whether a given article is associated to A. thaliana  ... 
doi:10.1093/nar/gkp484 pmid:19520768 pmcid:PMC2703909 fatcat:2jjdk7efzrcwdowjgqbdhxwctm

Information retrieval in an infodemic: the case of COVID-19 publications [article]

Sohrab Ferdowsi, Nikolay Borissov, Elaham Kashani, David Vicente Alvarez, Jenny Copara, Racha Gouareb, Poorya Amini, Douglas Teodoro
2021 bioRxiv   pre-print
We discuss different components of our architecture consisting of traditional information retrieval models, as well as modern neural natural language processing algorithms.  ...  In the context of searching for COVID-19 related scientific literature, we present an information retrieval methodology for effectively finding relevant publications for different information needs.  ...  First-stage retrieval: pre-processing, querying strategies and model fine-tuning In the first-stage retrieval step, we apply a classical NLP pre-processing pipeline to the publications (indexing phase)  ... 
doi:10.1101/2021.01.29.428847 fatcat:s6m7p3uukbaahac5vskbfrk4oi

Comparative of Mediator Approach for Database Integration

Mohd Kamir Yusof, Md Yazid Mohd Saman, Wan Nor Shuhadah Wan Nik
2015 Journal of Computer Science  
Acknowledgment The researchers would like to thank Universiti Sultan Zainal Abidin for providing facilities and services to do this research.  ...  All applications in Table 5 use XML for data exchange and wrapper as a mediator to receive query for searching and retrieving process and send a result to users.  ...  Advanced search can be used for advanced searching, where an image is provided by the user (using similarity) or as a free text (full text search) or by stipulating restrictions on the basis of the metadata  ... 
doi:10.3844/jcssp.2015.204.217 fatcat:v3xwfbhyvzfjno33l63qt3aafe

Systematic review of question answering over knowledge bases

Arnaldo Pereira, Alina Trifan, Rui Pedro Lopes, José Luís Oliveira
2021 IET Software  
The inclusion criteria rationale was English full-text articles published since 2015 on methods and systems for KBQAs.  ...  Querying services require knowledge beyond the typical user's expertise, which is a critical issue in adopting semantic information solutions.  ...  The query-generation (QG) process of a QA pipeline occurs after the entity and relation linking subtasks. Zafar et al.  ... 
doi:10.1049/sfw2.12028 fatcat:uuhsewdvsnal5hwua3lecfexqi

The Qanary Ecosystem: Getting New Insights by Composing Question Answering Pipelines [chapter]

Dennis Diefenbach, Kuldeep Singh, Andreas Both, Didier Cherix, Christoph Lange, Sören Auer
2017 Lecture Notes in Computer Science  
To address these issues we developed the knowledge-based Qanary methodology for choreographing QA pipelines distributed over the Web.  ...  , information retrieval, speech recognition and semantic technologies.  ...  We would like to thank Elena Demidova for proof-reading.  ... 
doi:10.1007/978-3-319-60131-1_10 fatcat:gfuwcmi6b5azppj674dlbvmx5e

Content-based document image retrieval in complex document collections

G. Agam, S. Argamon, O. Frieder, D. Grossman, D. Lewis, Xiaofan Lin, Berrin A. Yanikoglu
2007 Document Recognition and Retrieval XIV  
Our prototype automatically generates rich metadata about a complex document and then applies query tools to integrate the metadata with text search.  ...  Such complex document information processing combines several forms of image processing together with textual/linguistic processing to enable effective analysis of complex document collections, a necessity  ...  Acknowledgments This work is supported in part by a Challenge Workshop grant from ARDA.  ... 
doi:10.1117/12.703163 dblp:conf/drr/ArgamonFGL07 fatcat:v73nietpbvh6ldxxb6ouzi6u6i
« Previous Showing results 1 — 15 out of 3,615 results