Filters








3,150 Hits in 2.4 sec

Seeding Strategies for Semantic Disambiguation

Annika Hinze, David Bainbridge, Rebekah Wilkins, Craig Taube-Schock, J. Stephen Downie
2018 Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries - JCDL '18  
This paper introduces the seeding algorithm and explores seeding strategies for identifying these initial concepts in text volumes, such as books, that are stored in a digital library.  ...  Semantic disambiguation determines the meaning of words and phrases in a text, for which we use an automatically-generated Concept-in-Context (CiC) network.  ...  SEEDING FOR DISAMBIGUATION The disambiguation process has two phases: seeding and full semantic analysis.  ... 
doi:10.1145/3197026.3203874 dblp:conf/jcdl/Hinze0WTD18 fatcat:3m5frlvceza65d5kn3qkx5yrjy

Knowledge Base Unification via Sense Embeddings and Disambiguation

Claudio Delli Bovi, Luis Espinosa Anke, Roberto Navigli
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
We present KB-UNIFY, a novel approach for integrating the output of different Open Information Extraction systems into a single unified and fully disambiguated knowledge repository.  ...  KB-UNIFY consists of three main steps: (1) disambiguation of relation argument pairs via a sensebased vector representation and a large unified sense inventory; (2) ranking of semantic relations according  ...  We thus devised a disambiguation strategy that comprises three successive steps: 1.  ... 
doi:10.18653/v1/d15-1084 dblp:conf/emnlp/BoviAN15 fatcat:algllldpjfcvllbkgjhypz3kvi

Disambiguating identity web references using Web 2.0 data and semantics

Matthew Rowe, Fabio Ciravegna
2010 Journal of Web Semantics  
We present a methodology for generating this background knowledge by exporting data from multiple Web 2.0 platforms as RDF data models and combining these models together for use as seed data.  ...  how the semantics of data supports the intrinsic functionalities of these techniques.  ...  In order for our disambiguation techniques to function the RDF models of the web resources to be disambiguated must have semantics which are consistent with the seed data.  ... 
doi:10.1016/j.websem.2010.04.005 fatcat:lu5d4gztbvd23jjys4oew3wsfe

Disambiguating Identity Web References Using Web 2.0 Data and Semantics

Matthew Rowe, Fabio Ciravegna
2010 Social Science Research Network  
We present a methodology for generating this background knowledge by exporting data from multiple Web 2.0 platforms as RDF data models and combining these models together for use as seed data.  ...  how the semantics of data supports the intrinsic functionalities of these techniques.  ...  In order for our disambiguation techniques to function the RDF models of the web resources to be disambiguated must have semantics which are consistent with the seed data.  ... 
doi:10.2139/ssrn.3199481 fatcat:pl3vfuyhozcixl5gnigioltxem

Kanopy: Analysing the Semantic Network around Document Topics [chapter]

Ioana Hulpuş, Conor Hayes, Marcel Karnstedt, Derek Greene, Marek Jozwowicz
2013 Lecture Notes in Computer Science  
Besides the common task of semantic annotation of documents, Kanopy analyses the semantic network that resides in DBpedia around extracted concepts.  ...  The system's main novelty lies in the translation of social network analysis measures to semantic networks in order to find suitable topic labels.  ...  The applied linkage strategy and cut-off point can be adjusted from the user interface. After this stage, we obtain several clusters of noun phrases. Concept linking & disambiguation.  ... 
doi:10.1007/978-3-642-40994-3_53 fatcat:bdagj7bm5jamllv5wyhuswzhoe

Improving image sets through sense disambiguation and context ranking

Anthony R. Buck, Walterio W. Mayol
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
We propose that, in extension, improvement can be achieved in relevance, noise-reduction and completeness through sense disambiguation and contextual meta-data prepossessing.  ...  Within the paper we investigate different schemes for keyword set construction; ontology exclusive and authority extended, along with three differing ranking mechanisms.  ...  ACKNOWLEDGMENT The authors would like to thank the EPSRC for there supportive funding of the first authors DTA grant.  ... 
doi:10.1109/icsmc.2009.5346266 dblp:conf/smc/BuckM09 fatcat:tr5qjhtmdjdznaburglvyrm2r4

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

Niket Tandon, Gerard de Melo, Gerhard Weikum
2017 Proceedings of ACL 2017, System Demonstrations  
Despite important progress in the area of intelligent systems, most such systems still lack commonsense knowledge that appears crucial for enabling smarter, more human-like decisions.  ...  In this paper, we present a system based on a series of algorithms to distill fine-grained disambiguated commonsense knowledge from massive amounts of text.  ...  Our method considers joint semantic role labeling and word sense disambiguation for parsing these scripts to generate candidate items for the activity frames.  ... 
doi:10.18653/v1/p17-4020 dblp:conf/acl/TandonMW17 fatcat:vc7s4itddbfdvbkhrrshdtnlku

Unsupervised Approach to Word Sense Disambiguation in Malayalam

K.P. Sruthi Sankar, P.C. Reghu Raj, V. Jayan
2016 Procedia Technology - Elsevier  
For each possible sense of the ambiguous word, a relatively small set of training examples (seed sets) are identified which represents the sense.  ...  Seed set expansion module extends the seed set by adding most similar words to the seed set elements. These extended sets act as sense clusters.  ...  Bhadran V K, Associate Director, Centre for Development of Advanced Computing, for his sincere directions imparted with the project.  ... 
doi:10.1016/j.protcy.2016.05.106 fatcat:xdmg3pgokzdnnnbymmnsl5g3c4

Question Answering System using Multiple Information Source and Open Type Answer Merge

Seonyeong Park, Soonchoul Kwon, Byungsoo Kim, Sangdo Han, Hyosup Shim, Gary Geunbae Lee
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations  
We develop open semantic answer type detector for answer merging and improve previous developed single QA modules such as knowledge base based QA, information retrieval based QA.  ...  This paper presents a multi-strategy and multisource question answering (QA) system that can use multiple strategies to both answer natural language (NL) questions and respond to keywords.  ...  Acknowledgments This work was supported by the ICT R&D program of MSIP/IITP [R0101-15-0176, Development of Core Technology for Human-like Selftaught Learning based on a Symbolic Approach].  ... 
doi:10.3115/v1/n15-3023 dblp:conf/naacl/ParkKKHSL15 fatcat:2jqfj44syvd3xev4fae56eep4i

Page 157 of Computational Linguistics Vol. 24, Issue 1 [page]

1998 Computational Linguistics  
The results of disambiguation strategies reported for pseudo- words and the like are consistently above 95% overall accuracy, far higher than those reported for disambiguating three or more senses of polysemous  ...  Results for the 12 pairs of homographs re- ported are almost perfect. In his paper, Yarowsky suggests WordNet as a source for the seed collocations—a suggestion that we pursue in the next section.  ... 

Multimodal concept-dependent active learning for image retrieval

King-Shy Goh, Edward Y. Chang, Wei-Cheng Lai
2004 Proceedings of the 12th annual ACM international conference on Multimedia - MULTIMEDIA '04  
., the kernel-parameters and the sampling strategy are identically chosen) for learning query concepts of differing complexity.  ...  We then propose a multimodal learning approach that uses images' semantic labels to guide a concept-dependent, active-learning process.  ...  The angle diversity (AD) sampling strategy is used as the baseline for comparing the performance of the other algorithms used to modify the sample pool, namely disambiguate inputspace (DS) and disambiguate  ... 
doi:10.1145/1027527.1027664 dblp:conf/mm/GohCL04 fatcat:yq5qccle7vf7dnkiz65j2ttx7a

A Resource-Based Method for Named Entity Extraction and Classification [chapter]

Pablo Gamallo, Marcos Garcia
2011 Lecture Notes in Computer Science  
Languageindependent heuristics are used to disambiguate and classify entities that have been already identified (or recognized) in text.  ...  We compare the performance of our resource-based system with that of a supervised NEC module implemented for the FreeLing suite, which was the winner system in CoNLL-2002 competition.  ...  In particular, their extraction strategy requires some lists of seed named entities to generate queries and retrieve Web pages containing occurrences of the seed entities.  ... 
doi:10.1007/978-3-642-24769-9_44 fatcat:zmie64z2lrfpfdbrvq4lzwqhoq

Generating Training Data for Semantic Role Labeling based on Label Transfer from Linked Lexical Resources

Silvana Hartmann, Judith Eckle-Kohler, Iryna Gurevych
2016 Transactions of the Association for Computational Linguistics  
The automatically labeled training data (www.ukp.tu-darmstadt.de/ knowledge-based-srl/) are evaluated on four corpora from different domains for the tasks of word sense disambiguation and semantic role  ...  We present a new approach for generating role-labeled training data using Linked Lexical Resources, i.e., integrated lexical resources that combine several resources (e.g., Word-Net, FrameNet, Wiktionary  ...  We thank the action editors and anonymous reviewers for their thoughtful comments. Additional thanks go to Nancy Ide and Collin Baker for providing the MASC dataset.  ... 
doi:10.1162/tacl_a_00093 fatcat:cirmmv7qmrao7btya4lpcyokge

Automatic Construction and Global Optimization of a Multisentiment Lexicon

Xiaoping Yang, Zhongxia Zhang, Zhongqiu Zhang, Yuting Mo, Lianbei Li, Li Yu, Peican Zhu
2016 Computational Intelligence and Neuroscience  
In order to distinguish the sentiment polarities of those words which may express either positive or negative meanings in different contexts, we further present a sentiment disambiguation algorithm to  ...  Lastly, we present a global optimization framework that provides a unified way to combine several human-annotated resources for learning our 10-dimensional sentiment lexicon SentiRuc.  ...  Computational Intelligence and Neuroscience language models depend a lot on the correspondence of inner semantics and outer grammars; thus, it is of great significance to research how to comprehend and  ... 
doi:10.1155/2016/2093406 pmid:28042290 pmcid:PMC5153545 fatcat:ev2x2j7r3bg6djnriwo363jiwa

Situated Structure Learning of a Bayesian Logic Network for Commonsense Reasoning [article]

Haley Garrison, Sonia Chernova
2016 arXiv   pre-print
This paper details the implementation of an algorithm for automatically generating a high-level knowledge network to perform commonsense reasoning, specifically with the application of robotic task repair  ...  For example, if a seed word was incorrectly disambiguated, the relations added from ConceptNet would often be related to the incorrect sense of the seed word.  ...  Seed Word Disambiguation After the seed words have been collected, they must be disambiguated to determine the contextually correct senses of the words.  ... 
arXiv:1607.00428v1 fatcat:jz3bkmptdvbfxjksacgq5gasz4
« Previous Showing results 1 — 15 out of 3,150 results