2,432 Hits in 9.3 sec

Natural language processing for information retrieval

David D. Lewis, Karen Spärck Jones
1996 Communications of the ACM  
focus on the potential role of natural language processing.  ...  The paper summarizes the essential properties of document retrieval and reviews both conventional practice and research findings, the latter suggesting that simple statistical techniques can be effective  ...  We will use 'natural language' in this sense of drawing indexing terms from the document itself, and use 'NLP' when referring to natural language processing.  ... 
doi:10.1145/234173.234210 fatcat:hx5vubhmcvctdcwemnxhu6qpem

Natural Language Processing and Information Retrieval [chapter]

Ellen M. Voorhees
1999 Lecture Notes in Computer Science  
Information retrieval addresses the problem of nding those documents whose content matches a user's request from among a large collection of documents.  ...  Several factors contribute to the di culty of improving on a good statistical baseline including: the forgiving nature but broad coverage of the typical retrieval task; the lack of good weighting schemes  ...  Acknowledgements My thanks to Donna Harman and Chris Buckley for improving this paper through their comments.  ... 
doi:10.1007/3-540-48089-7_3 fatcat:bgh5hwznava75gmiuuzy4jnphy

A review of ontology based query expansion

J. Bhogal, A. Macfarlane, P. Smith
2007 Information Processing & Management  
This paper examines the meaning of context in relation to ontology based query expansion and contains a review of query expansion approaches.  ...  Finally the area of further research in applying context from an ontology to query expansion within a newswire domain is described.  ...  Language models are based on statistical language modelling (SLM) such that a language model is a probability distribution that captures statistical regularities of natural language use.  ... 
doi:10.1016/j.ipm.2006.09.003 fatcat:thcrluuhuvbgrcqmc43amhwqsm

Building a Chinese Collocation Bank

2009 International Journal of Computer Processing Of Languages  
Through statistical analysis on the collocation bank, some interesting characteristics of Chinese bigram collocations are presented in this paper.  ...  The definition and properties are first studied. Based on a combination of different properties, a classification scheme is proposed to categorize Chinese collocations into four types.  ...  Consequently, collocation knowledge are widely employed in many natural language processing (NLP) tasks, such as in word sense disambiguation, machine translation, information retrieval and natural language  ... 
doi:10.1142/s1793840609002019 fatcat:56osx54wprg4dcjdarwvo373ri

Synthesizer: Expediting synthesis studies from context-free data with natural language processing [article]

Lisa Gandy, Jordan Gumm, Benjamin Fertig, Michael J Kennish, Sameer Chavan, Ann Thessen, Luigi Marchionni, Xiaoxan Xia, Shambhavi Shankrit, Elana J Fertig
2016 bioRxiv   pre-print
We propose a novel natural language processing (NLP) algorithm, Synthesize, to merge data annotations automatically.  ...  However, accurately combining records from diverse studies requires tedious and error-prone human curation, posing a significant barrier to synthesis studies.  ...  Therefore, we propose a novel natural language processing algorithm to mine and standardize data tables by introducing semantic context.  ... 
doi:10.1101/053629 fatcat:dvmldsjlm5hvxpqd67pf3nf754

New trends in terminology processing and implications for practical translation

Blaise Nkwenti‐Azeh
1994 ASLIB Proceedings  
This paper examines how the changes currently taking place in terminology processing and documentation are related to the multilingual needs of translation, and also how progress in natural language processing  ...  The paper concludes by identifying some specific areas in terminology software development which can benefit from the expertise of translators and other language professionals.  ...  INTRODUCTION Terminology is now firmly established and widely recognised as a distinct area of study concerned with the vocabulary of special subject languages, valiantly referred to as "Languages for  ... 
doi:10.1108/eb051345 fatcat:mae4mcpi2jhmzleulokjzg5k5y

Complex event processing for content-based text, image, and video retrieval

Elizabeth K Bowman, Barbara D Broome, V Melissa Holland, Douglas Summers-Stay, Raghuveer M Rao, John Duselis, Jonathan Howe, Bhopinder K Madahar, Anne-Claire Boury-Brisset, Bruce Forrester, Peter Kwantes, Gertjan Burghouts (+2 others)
2016 2016 International Conference on Military Communications and Information Systems (ICMCIS)  
Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently  ...  Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, to Department of Defense, Washington Headquarters Services  ...  provision of relevant program/project technical information.  ... 
doi:10.1109/icmcis.2016.7496546 fatcat:g4omhjgggfb6zdlskc2564jgam

Introducing a New Scalable Data-as-a-Service Cloud Platform for Enriching Traditional Text Mining Techniques by Integrating Ontology Modelling and Natural Language Processing [chapter]

Alexey Cheptsov, Axel Tenschert, Paul Schmidt, Birte Glimm, Mauricio Matthesius, Thorsten Liebig
2014 Lecture Notes in Computer Science  
in a natural language.  ...  An important analytical task in a number of scientific and technological domains is to retrieve information from text data, aiming to get a deeper insight into the content represented by the data in order  ...  methods as well as template-based, self learning natural language processing technologies in order to ensure a fully automated, reliable, and efficient information retrieval.  ... 
doi:10.1007/978-3-642-54370-8_6 fatcat:qoxc6xntnbczlp247iak3fb7dm

A Study on the Application of Data-driven Learning in Vocabulary Teaching and Leaning in China's EFL Class

Xiaowei Guan
2013 Journal of Language Teaching and Research  
Data-driven learning (DDL) developed from corpus linguistics plays a pioneering role in the evolution of EFL teaching, allowing the learners to indentify and induce language rules by observing numerous  ...  Compared with traditional foreign language teaching and learning method, data-driven learning is characterized by "autonomic learning", "authentic language input", "self-discovery", and "bottomup inductive  ...  Yang (2002) holds the view that the applications of corpus are reflected in the statistics of language frequency, dictionary compilation, the study on vocabulary collocation, language teaching and natural  ... 
doi:10.4304/jltr.4.1.105-112 fatcat:cz7fzettrzfdfpcvbjwqdlqrvu

Matching meaning for cross-language information retrieval

Jianqiang Wang, Douglas W. Oard
2012 Information Processing & Management  
This article describes a framework for cross-language information retrieval that efficiently leverages statistical estimation of translation probabilities.  ...  The framework provides a unified perspective into which some earlier work on techniques for cross-language information retrieval based on translation probabilities can be cast.  ...  Introduction Cross-language Information Retrieval (CLIR) is the problem of finding documents that are expressed in a language different from that of the query.  ... 
doi:10.1016/j.ipm.2011.09.003 fatcat:rsoxmr67jrb3tmifyqgtk6kpwe

Long-range neural synchronization supports fast and efficient reading: EEG correlates of processing expected words in sentences

Nicola Molinaro, Paulo Barraza, Manuel Carreiras
2013 NeuroImage  
In this study, we analyzed the neurophysiological bases of sentence reading through the EEG activity elicited during reading the same word embedded in differently constraining contexts: a) a low-constraining  ...  context; b) a high-constraining semantic compositional context; c) a high-constraining collocational context in which the item was in final position of a multi-word fixed-order expression.  ...  NM was partially supported by a 'Juan de la Cierva' grant from the Spanish Government. PB was supported by the associative research program CONICYT, Project CIE-05.  ... 
doi:10.1016/j.neuroimage.2013.01.031 pmid:23357072 pmcid:PMC3817365 fatcat:znc4dric2nfkrpoxd3oamqkpza

Leveraging Cognitive Search Patterns to Enhance Automated Natural Language Retrieval Performance [article]

Bhawani Selvaretnam, Mohammed Belkhatir
2020 arXiv   pre-print
Over the past two decades, a significant body of works has advanced technical retrieval prowess while several studies have shed light on issues pertaining to human search behavior.  ...  terms adopted in the retrieval process.  ...  incorporating linguistic, statistical and semantic-based techniques in the information retrieval process.  ... 
arXiv:2004.10035v1 fatcat:ogp646o7cvekhffvdbfr3xjpum

A Cascaded Classification Approach to Semantic Head Recognition

Lukas Michelbacher, Alok Kothari, Martin Forst, Christina Lioma, Hinrich Schütze
2011 Conference on Empirical Methods in Natural Language Processing  
We achieve an accuracy of 68% for recognizing non-compositional MWUs and show that our MWU recognizer improves retrieval performance when used as part of an information retrieval system.  ...  In this paper, we propose a new cascaded model for detecting MWUs of arbitrary length for tokenization, focusing on noun phrases in the physics domain.  ...  This section illustrates one way of adjusting the retrieval process so that non-compositional phrases are processed as semantic entities that may enhance retrieval performance.  ... 
dblp:conf/emnlp/MichelbacherKFLS11 fatcat:clt7bwd56fdk5dhcc2px66hujm

A study of the metadata creation behavior of different user groups on the Internet

Jin Zhang, Iris Jastram
2006 Information Processing & Management  
Metadata is designed to improve information organization and information retrieval effectiveness and efficiency on the Internet.  ...  This study will enhance the current understanding of metadata application behavior and provide evidence useful to researchers, web publishers, and search engine designers.  ...  People may not associate them, however, with knowledge of and practice in indexing and describing their sites through metadata.  ... 
doi:10.1016/j.ipm.2005.05.002 fatcat:bq7iyzqkbffptinhmbbcocg3ea

Individual Chunking Ability Predicts Efficient or Shallow L2 Processing: Eye-Tracking Evidence From Multiword Units in Relative Clauses

Manuel F. Pulido
2021 Frontiers in Psychology  
Behavioral studies on language processing rely on the eye-mind assumption, which states that the time spent looking at text is an index of the time spent processing it.  ...  Because earlier studies did not identify a reliable predictor of variability in L2 processing, such uncertainty around the interpretation of reading times introduces a potential confound that undermines  ...  A recently developed measure of chunk sensitivity was employed as an index of processing efficiency in each of participants' two languages.  ... 
doi:10.3389/fpsyg.2020.607621 pmid:33519614 pmcid:PMC7844092 fatcat:277izdkrhrbz5du43kvus75y4e
« Previous Showing results 1 — 15 out of 2,432 results