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.
Filters
Consistent Validation of Manual and Automatic Sense Annotations with the Aid of Semantic Graphs
2006
Computational Linguistics
Preserved Fulltext
In this article, we introduce Valido, a visual tool for the validation of manual and automatic sense annotations. ...
The task of annotating texts with senses from a computational lexicon is widely recognized to be complex and often subjective. ...
In this article, we present Valido, a tool for supporting the validation of both manual and automatic sense annotations through the use of semantic graphs, particularly of semantic interconnection patterns ...
doi:10.1162/coli.2006.32.2.273
fatcat:vefyzqlqhna2zfrebgmafid564
Valido
2006
Proceedings of the COLING/ACL on Interactive presentation sessions -
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 validator can analyse the semantic graphs resulting from each sense choice and decide which sense is more coherent with respect to the structure of the adopted lexicon. ...
We describe the interface and report an evaluation of the tool in the validation of manual sense annotations. ...
Acknowledgments This work is partially funded by the Interop NoE (508011), 6 th European Union FP. ...
doi:10.3115/1225403.1225407
dblp:conf/acl/Navigli06a
fatcat:3xqwt7u5abf3rmp4f4yy7bnywe
A structural approach to the automatic adjudication of word sense disagreements
2008
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 2009; you can also visit the original URL.
The file type is application/pdf.
The semantic annotation of texts with senses from a computational lexicon is a complex and often subjective task. ...
We perform a twofold experimental evaluation of the approach applied to manual annotations from the SemCor corpus, and automatic annotations from the Senseval-3 English all-words competition. ...
We wish to thank Francesco Maria Tucci, Giuliana and Maria Luisa Pesaresi, and Orin Hargraves for their invaluable support. ...
doi:10.1017/s1351324908004749
fatcat:x2awksfwhvb3rgqfkuminyxiju
Knowledge-based interaction in software development
2011
International Journal of Intelligent Decision Technologies
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.
Building a knowledge base with software artefacts by using the KnowBench system can then be exploited by semantic search engines or P2P metadata infrastructures in order to foster the dissemination of ...
However, current software development environments are "syntactic", i.e. they do not facilitate understanding the semantics of software artefacts and hence cannot fully support the knowledge-driven activities ...
-Zooming in/out the whole graph.
Manual semantic annotation of source code An important aspect of the KnowBench is the ability to annotate semantically source code. ...
doi:10.3233/idt-2011-0104
fatcat:frfakjbg4rcjhnc5h7xzsq7jha
Scalable Semantic Annotation of Text Using Lexical and Web Resources
[chapter]
2010
Lecture Notes in Computer 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 2015; you can also visit the original URL.
The file type is application/pdf.
In this paper we are dealing with the task of adding domainspecific semantic tags to a document, based solely on the domain ontology and generic lexical and Web resources. ...
The method comprises a novel combination of measures of semantic relatedness and word sense disambiguation techniques, in order to identify the most related ontology concepts for the document. ...
The proposed method consists of a novel combination of measures of semantic relatedness and word sense disambiguation techniques, in order to identify the most related ontology concepts for a given document ...
doi:10.1007/978-3-642-12842-4_32
fatcat:psidkkvpe5dapm35ocp5cefnpm
Towards a universal wordnet by learning from combined evidence
2009
Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09
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.
We propose a methodology for the automatic construction of a large-scale multilingual lexical database where words of many languages are hierarchically organized in terms of their meanings and their semantic ...
Lexical databases are invaluable sources of knowledge about words and their meanings, with numerous applications in areas like NLP, IR, and AI. ...
The input graph G0 does not cover any of the validation arcs, and thus has a recall and F1-score of 0%. ...
doi:10.1145/1645953.1646020
dblp:conf/cikm/MeloW09
fatcat:wnvulr5lbjhlnlmfatn57nsacm
Weakly Supervised Word Sense Disambiguation Using Automatically Labelled Collections
2021
Proceedings of the Institute for System Programming of RAS
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.
To cope with the knowledge acquisition bottleneck in Russian, we first utilized the method based on the concept of monosemous relatives to automatically generate a labelled training collection. ...
State-of-the-art supervised word sense disambiguation models require large sense-tagged training sets. However, many low-resource languages, including Russian, lack such a large amount of data. ...
This research has been supported by the Interdisciplinary Scientific and Educational School of Lomonosov Moscow State University "Brain, Cognitive Systems, Artificial Intelligence". ...
doi:10.15514/ispras-2021-33(6)-13
fatcat:dlrlnm5jafdfhmg6bfsihl3qaa
Semantic Annotation and Querying Framework based on Semi-structured Ayurvedic Text
[article]
2022
arXiv
pre-print
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.
We hope that the knowledge graph that we have created through manual annotation and subsequent curation will help in development and testing of NLP tools in future as well as studying of the Bhavaprakasanighantu ...
Thus, in this work, we describe our efforts on manual annotation of Sanskrit text for the purpose of knowledge graph (KG) creation. ...
Acknowledgements We thank Anil Kumar Gourishetty from IIT Roorkee for his help in connecting us with Sanskrit volunteers. ...
arXiv:2202.00216v1
fatcat:w7xx5g3a45eppmvkf6s25fzeoa
Collaboratively built semi-structured content and Artificial Intelligence: The story so far
2013
Artificial Intelligence
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.
Special thanks go to Jim McManus and all reviewers who contributed valuable feedback and ensured the papers contained in this special issue were of the highest quality. ...
Finally, we thank the Artificial Intelligence Journal Editors-in-Chief, Tony Cohn, Rina Dechter and Ray Perrault, for their continued support throughout the preparation of this special issue. ...
Thus, Mihalcea was able to automatically create sense-annotated data on the basis of a manual mapping: these data were then provided as input to a machine learning WSD system for predicting the senses ...
doi:10.1016/j.artint.2012.10.002
fatcat:mwk5o254urb2dejsh7c224uu3q
Unified Partial Configuration Model Framework for Fast Partially Occluded Object Detection in High-Resolution Remote Sensing Images
2018
Remote Sensing
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 2019; you can also visit the original URL.
The file type is application/pdf.
Recent partial configuration model (PCM) based methods deal with occlusion yet suffer from the problems of massive manual annotation, separate parameter learning, and low training and detection efficiency ...
The work in this paper is inspired from the problems in PCM and AFI-PCM, which tries to integrate the entire PCM model with a novel part sharing mechanism for both fast and automatic model training and ...
The semantic parts are defined manually and semantically, along with the skeleton graph of the category. ...
doi:10.3390/rs10030464
fatcat:pazbef3munhpdhcca7t4gpbboy
Automatic extraction of paraphrastic phrases from small-size corpora
2009
Lingvisticæ investigationes
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 knowledge is semi-automatically derived from the text collection, in interaction with a large semantic network. ...
In order to decrease the time spent on the elaboration of resources for NLP system (for example for Information Extraction), we suggest to use a knowledge acquisition module that helps extracting new information ...
The process is made of automatic steps and manual validation stages. The process is weakly supervised since the analyst only has to provide one example to the system. ...
doi:10.1075/li.32.1.04poi
fatcat:xhjxxbozjze5plvrz6yxvsmzxi
Labeling and Retrieval of Emotionally-Annotated Images using WordNet
[article]
2014
arXiv
pre-print
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 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Repositories of images with semantic and emotion content descriptions are valuable tools in many areas such as Affective Computing and Human-Computer Interaction, but they are also important in the development ...
Ever growing number of image documents available on the Internet continuously motivates research of better annotation models and more efficient retrieval methods which use mash-up of available data on ...
Acknowledgements Engineering and Computing. The WNtags tool can be accessed by contacting the first author of the paper. ...
arXiv:1304.0954v2
fatcat:pfd5zi7ssjhulhikbqvzjclnk4
Semantics-Driven Remote Sensing Scene Understanding Framework for Grounded Spatio-Contextual Scene Descriptions
2021
ISPRS International Journal of Geo-Information
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.
To minimize the semantic gap for remote-sensing-scene understanding, the framework puts forward the transformation of scenes by using semantic-web technologies to Remote Sensing Scene Knowledge Graphs ...
The knowledge-graph representation of scenes has been formalized through the development of a Remote Sensing Scene Ontology(RSSO)—a core ontology for an inclusive remote-sensing-scene data product. ...
Acknowledgments: The authors are grateful to the Google Cloud Research Credits Program for providing the credits that enabled the use of GCP for training and validating the deep-learning models. ...
doi:10.3390/ijgi10010032
fatcat:warifoopejaqfglljmkbatjrke
Ontological Semantic Annotation of an English Corpus Thorough Condition Random Fields
2019
Information
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.
Considering that annotation is an arduous task that demands time and specialized personnel to perform it, much is done on ways to implement the semantic annotation automatically. ...
In this sense, this article aims to present an automatic approach to enrich documents from the American English corpus through a CRF model for semantic annotation of ontologies from Schema.org top-level ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/info10050171
fatcat:jbbytuqnf5gfzat73nzqquqlzm
Surfing the Service Web
[chapter]
2003
Lecture Notes in Computer 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 2019; you can also visit the original URL.
The file type is application/pdf.
. support for semi-automatic composition and invocation of web services that have semantically heterogeneous descriptions. ...
In this paper we present an approach that combines the strength of the World Wide Web, viz. interlinked HTML pages for presentation and human consumption, with the strength of semantic web services, viz ...
A part of this work was funded by the SemIPort project of the federal ministry of education and research (BMBF). ...
doi:10.1007/978-3-540-39718-2_14
fatcat:z7vhqbymzzhgvdsmg63obwgbji
« Previous
Showing results 1 — 15 out of 6,267 results