A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Filters
Computational Language Systems: Architectures
[chapter]
2006
Encyclopedia of Language & Linguistics
Preserved Fulltext
in detail at algorithmic and data resource infrastructure; concludes with some thoughts on the future of the area. ...
The article: presents a critical review of the various approaches that have been taken in the field; analyses eleven categories of previous work and uses these categories to organise the discussion; looks ...
Other similar work in this area include: the XDOC workbench Rösner and Kunze (2002) ; Artola et al. (2002) report work on stand-off markup for NLP tools. ...
doi:10.1016/b0-08-044854-2/04367-4
fatcat:kdeje722dvhzzcz7alsycbqdwy
Software Architecture for Language Engineering
2004
Natural Language Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In order to demonstrate the theory developed in relation to SALE, we present the design, implementation and evaluation of GATE, a General Architecture for Text Engineering, which illustrates in practice ...
This thesis defines the boundaries of Software Architecture for Language Engineering (SALE), an area formed by the intersection of human language computation and software engineering. ...
Applications are complete software systems that perform some intrinsically useful task, and may be sold as products. For example, a translator's workbench is an application 2 . ...
doi:10.1017/s1351324904003481
fatcat:xzkpj2edozgidfrknmergcyyga
D5.1 Report on Vocabularies for Interoperable Language Resources and Services
2020
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This document provides a survey over vocabularies for language resources and services and sketch necessary extensions and the expected contribution of the Prêt-à-LLOD project to their further development ...
We focus on three main aspects of linguistically analyzed data 1. lexical-conceptual resources, i.e., repositories of terminology, lexical data, translation, and semantics, 2. linguistically annotated ...
SynAF proposes thus an integrated view on those two types of annotation, within the context of a graph representation. ...
doi:10.5281/zenodo.5744205
fatcat:xfrpsie7zjgjboxi4j265husjy
Selected Information Management Resources for Implementing New Knowledge Environments: An Annotated Bibliography
2012
Scholarly and Research Communication
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This annotated bibliography reviews scholarly work in the area of building and analyzing digital document collections with the aim of establishing a baseline of knowledge for work in the field of digital ...
Each of these is then further divided into sub-topics to provide a broad snapshot of modern information management techniques for building and analyzing digital documents collections. ...
This kernel was built upon considerably by Alex Garnett, working consultatively with Cara Letich, Ray Siemens, and members of the Implementing New Knowledge Environment (INKE) and Public Knowledge Project ...
doi:10.22230/src.2012v3n1a52
fatcat:iug7tyszcbg3hdw4siqinlh5vy
Natural Language Processing as a Foundation of the Semantic Web
2007
Foundations and Trends® in Web Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Acknowledgments CB would like to thank José Iria for help in discussing and formulating the Abraxas model, and Ziqi Zhang for undertaking parts of the implementation and evaluation. ...
CB has been supported in this work by the EPSRC project Abraxas (http://nlp.shef.ac.uk/abraxas/) under grant number GR/T22902/01 and the EC funded IP Companions IST-034434 (www.companionsproject.org) ...
library" (1990). (4) "What therefore is needed to give effect to the vision is the internal provision of (hypertext) objects and links, and specifically in the strong form of an AI-type knowledge base ...
doi:10.1561/1800000002
fatcat:n2xfw3qdhverrokidb2globwyq
Why Standardization Efforts Fail
2011
Journal of Electronic Publishing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
AsLing (International Association for Advancement in Language Technology), which took over the organisation of this conference in 2014, is proud to present the proceedings of Translating and the Computer ...
Preface For the past 38 years the international conference Translating and the Computer has been a leading and distinctive forum for academics, users, developers and vendors of computer aids for translators ...
Huaqing Hong at Nanyang Technological University (Singapore) for sharing with me some of the tools used in this research. ...
doi:10.3998/3336451.0014.103
fatcat:dmw2l6nx5vaola6zjohsfggg7m
Pattern-based segmentation of digital documents
2008
ACM SIGWEB Newsletter
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The central part of my work consists of discussing that model, investigating how a digital document can be segmented, and how a segmented version can be used to implement advanced tools of conversion. ...
IML is a general and extensible language, which basically adopts an XHTML syntax, able to capture a posteriori the only content of a digital document. ...
It is an optional feature of SGML usable to annotate concurrent hierarchical structures in a single document. ...
doi:10.1145/1350502.1350505
fatcat:jjczizjwjfbi7ovtznqrmanlsq
Automatic document-level semantic metadata annotation using folksonomies and domain ontologies
2008
ACM SIGWEB Newsletter
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The tool was applied to a case study consisting of a framework for evaluating the usefulness of the generated semantic metadata within the context of a particular eLearning application. ...
This thesis presents a novel tool that uses folksonomies to automatically generate metadata with educational semantics in an attempt to provide semantic annotations to bookmarked web resources, and to ...
As an example, the tag 'library' is an instance in the resource type ontology, which means 'a collection of things'. ...
doi:10.1145/1408940.1408944
fatcat:hgidhenczvbldmqhcptooyspvu
Metadata model for interactions of 3D objects
2008
2008 1st International Conference on Information Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The XQuery is for XML like SQL for relational databases. It allows extracting and manipulating data from XML documents or any data source that can be viewed as being in the XML format. ...
The IMQL integrates with Interaction Interface definitions permitting the use of new object parameter types and value data included directly in the query. ...
Consider a teacher from Poland who wants to prepare a lecture on the eye anatomy and reactions to light. He/she has to search the repository for appropriate models. ...
doi:10.1109/inftech.2008.4621648
fatcat:z76gic45szgwjjvedu6s63c5ma
Wikipedia-based Semantic Interpretation for Natural Language Processing
2009
The Journal of Artificial Intelligence Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our method represents meaning in a high-dimensional space of concepts derived from Wikipedia, the largest encyclopedia in existence. ...
Here we propose a novel method, called Explicit Semantic Analysis (ESA), for fine-grained semantic interpretation of unrestricted natural language texts. ...
Lee and Brandon Pincombe for making available their document similarity data. ...
doi:10.1613/jair.2669
fatcat:mwcky2jqx5e6zimhzgsbh5rffa
New publication cultures in the humanities: exploring the paradigm shift
2015
ChoiceReviews
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The first type of annotation consists of a linguistic, stylistic, or other type of evaluation note of the text during the study phase. ...
Annotations represent a particular problem as they contain different types of data. ...
to New Publication Cultures in the Humanities offer a bracing vision of scholarly research as an open-ended and collaborative enterprise -a vision that this stimulating collection both advances and exemplifies ...
doi:10.5860/choice.189021
fatcat:sniykmljung25fobj7ofnmr3ke
:{unav)
2012
Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Appendix C describes the tokenizing library at the heart of all learning algorithms implemented for this thesis. ...
A central question addressed in these experiments is how well SRV can make use of the linguistic information provided by two off-the-shelf NLP packages, one a syntactic parser, the other a semantic lexicon ...
Some characteristics of the document collection are shown in Table A .l, and of the individual fields in Table A .2. ...
doi:10.1023/a:1007601113994
fatcat:wcvf75mpmreaxnp4tubluatbx4
Feature generation for textual information retrieval using world knowledge
2007
SIGIR Forum
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2009; you can also visit the original URL.
The file type is application/pdf.
In such cases, there exists a trade-off between the size of the feature space and the amount of training documents that can be used for learning. ...
Reuters-21578 is a cleaned version of the earlier release named Reuters-22173, which contained errors and duplicate documents. The collection contains 21578 documents (hence the name) in SGML format. ...
doi:10.1145/1328964.1328988
fatcat:blfxbh3jijfqpemo756gpyobs4
Social Networks and the Semantic Web
2015
Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
For example, NLP is tied to the notions of annotation and ontology learning. ...
A number of libraries and tools have been written in a variety of programming languages for dealing with PFIF data. ...
Contribution to the Linguistic Analysis of Business Conversations within the Language/Action Perspective
1998-4 Dennis Breuker (UM) Memory versus Search in Games ...
doi:10.1145/2740908.2742138
dblp:conf/www/Mika15
fatcat:ptyntdmnjrc4tcayyytykwlaba
Editors' Preface
2021
Variants
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
It is easier to implement such connections on the level of metadata, as it is easier to standardize this type of data than it is to standardize text annotation. ...
Finally, once a certain amount of text has been translated in this way, digital tools like NLP can be developed based on the training data to automate the translation process to some degree. ...
Restricted Translation of Historical Dutch Text
Hugo Maat Abstract: This article proposes an experimental approach to the diachronic translation of document sources written in historical variants of ...
doi:10.4000/variants.1239
fatcat:ka26dx266nfhxdbjxcqbfmsala
« Previous
Showing results 1 — 15 out of 37 results