Filters








504 Hits in 3.5 sec

Semantic Relatedness for Keyword Disambiguation: Exploiting Different Embeddings [article]

María G. Buey and Carlos Bobed and Jorge Gracia and Eduardo Mena
2020 arXiv   pre-print
Building on previous works, we present a semantic relatedness measure that uses word embeddings, and explore different disambiguation algorithms to also exploit both word and sentence representations.  ...  In this paper, we propose an approach to keyword disambiguation which grounds on a semantic relatedness between words and senses provided by an external inventory (ontology) that is not known at training  ...  CONCLUSIONS AND FUTURE WORK In this paper, we have presented a keyword disambiguation approach based on a semantic relatedness measure which exploits the semantic information captured by word embeddings  ... 
arXiv:2002.11023v1 fatcat:uzyyqmimonbyhd5qx4sfwqso5i

A Domain Independent Semantic Measure for Keyword Sense Disambiguation

María G. Buey, Carlos Bobed, Jorge Gracia, Eduardo Mena
2021 Zenodo  
Our approach grounds on a semantic relatedness measure between words and concepts, and explores different disambiguation algorithms to study the contribution of both word and sentence-level representations  ...  Understanding the user's intention is crucial for many tasks that involve human-machine interaction. To that end, word sense disambiguation (WSD) techniques play an important role.  ...  CONCLUSIONS AND FUTURE WORK In this paper we have presented a keyword disambiguation approach based on a semantic relatedness measure which exploits the semantic information captured by word embeddings  ... 
doi:10.5281/zenodo.4631684 fatcat:vdu3jzuzonfvzejc4dwewepkwy

System for collective entity disambiguation

Ashish Kulkarni, Kanika Agarwal, Pararth Shah, Sunny Raj Rathod, Ganesh Ramakrishnan
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
We present an approach and a system for collective disambiguation of entity mentions occurring in natural language text. Given an input text, the system spots mentions and their candidate entities.  ...  Our model also allows for a natural treatment of mentions that either have no entity attached or have more than one attachments.  ...  [22] for instance, uses context overlap for disambiguation and combines it with a classifier model that exploits local and topical features.  ... 
doi:10.1145/2633211.2639488 dblp:conf/sigir/KulkarniASRR14 fatcat:lltwvvctb5bhtot3vggk5ubjki

Word sense disambiguation

Roberto Navigli
2009 ACM Computing Surveys  
The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks.  ...  Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner.  ...  The author wishes to thank Francesco Maria Tucci for his invaluable support, Paola Velardi for her encouragement and advice, Ed Hovy for his useful remarks on an early version of this work, and Diana McCarthy  ... 
doi:10.1145/1459352.1459355 fatcat:jchhwe4xcjbbnjsqblynshli7i

Word Sense Disambiguation for Exploiting Hierarchical Thesauri in Text Classification [chapter]

Dimitrios Mavroeidis, George Tsatsaronis, Michalis Vazirgiannis, Martin Theobald, Gerhard Weikum
2005 Lecture Notes in Computer Science  
We argue that the high precision exhibited by our WSD algorithm in various humanly-disambiguated benchmark datasets, is appropriate for the classification task.  ...  The introduction of hierarchical thesauri (HT) that contain significant semantic information, has led researchers to investigate their potential for improving performance of the text classification task  ...  Another important issue for the successful embedding of WSD in text classification, is the exploitation of senses' semantic relations, that are provided by the HT.  ... 
doi:10.1007/11564126_21 fatcat:5fx2q7mv6fbshm2bwwkvbelegm

Topic Level Disambiguation for Weak Queries

Hui Zhang, Kiduk Yang, Elin Jacob
2013 Journal of Information Science Theory and Practice  
However, existing IR approaches such as query expansion are not overly effective because they make little effort to analyze and exploit the meanings of the queries.  ...  Motivated by the demand for a robust IR system that can consistently provide highly accurate results, the proposed study implemented a novel topic detection that leveraged both the language model and structural  ...  Queries from the Blog and HARD collections were disambiguated using knowledge at two different semantic levels: Wikipedia and free text.  ... 
doi:10.1633/jistap.2013.1.3.3 fatcat:yu77pl66jndx3ifyu57spzj7wy

Word Sense Disambiguation Using Cosine Similarity Collaborates with Word2vec and WordNet

Korawit Orkphol, Wu Yang
2019 Future Internet  
Words have different meanings (i.e., senses) depending on the context. Disambiguating the correct sense is important and a challenging task for natural language processing.  ...  A word-embedding approach has an advantage in this issue.  ...  Figure 2 shows some examples of wsdw2v (Jupyter notebook for wsdw2v is available at https://anaconda.org/korawit/wsdw2v/notebook) to disambiguate word "bank" and "plant" in different contexts.  ... 
doi:10.3390/fi11050114 fatcat:zamxayjolbh2jnsiskm3cm7lw4

Exploring the Power of Supervised Learning Methods for Company Name Disambiguation in Microblog Posts

2019 Turkish Journal of Electrical Engineering and Computer Sciences  
More specifically, we generate several profiles for each organization, which contain richer information.  ...  Entity Ranking Algorithm For this algorithm, we use different profile vectors with different keyword sets. In Table 7 through Table 9 , the keyword sets are represented as tuples.  ...  We employ LSI on company Wikipedia pages to extract semantically related keywords for each company, and build another profile out of these keywords.  ... 
doi:10.3906/elk-1809-167 fatcat:cl6b6pnztzag5phlk2bw7pi7wq

Scalable Semantic Annotation of Text Using Lexical and Web Resources [chapter]

Elias Zavitsanos, George Tsatsaronis, Iraklis Varlamis, Georgios Paliouras
2010 Lecture Notes in Computer Science  
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.  ...  In this manner, we avoid the need for trained domain-specific lexical resources, which hinder the scalability of semantic annotation.  ...  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

Semantic Measures for Keywords Extraction [chapter]

Davide Colla, Enrico Mensa, Daniele P. Radicioni
2017 Lecture Notes in Computer Science  
In this paper we introduce a minimalist hypothesis for keywords extraction: keywords can be extracted from text documents by considering concepts underlying document terms.  ...  The authors are also grateful to the anonymous reviewers for their valuable comments and suggestions.  ...  We desire to thank Simone Donetti and the Technical Staff of the Computer Science Department of the University of Turin, for their support in the setup and administration of the computer system used in  ... 
doi:10.1007/978-3-319-70169-1_10 fatcat:5s5ftrtb6jcjjd4ehhbwzynfl4

Collaboratively built semi-structured content and Artificial Intelligence: The story so far

Eduard Hovy, Roberto Navigli, Simone Paolo Ponzetto
2013 Artificial Intelligence  
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.  ...  semantic relatedness exploiting lexical resources such as WordNet.  ...  and disambiguation, Word Sense Disambiguation (WSD), and computing semantic relatedness.  ... 
doi:10.1016/j.artint.2012.10.002 fatcat:mwk5o254urb2dejsh7c224uu3q

Utilising Wikipedia for Text Mining Applications

Muhammad Atif Qureshi
2016 SIGIR Forum  
It introduces the most relevant definitions and the related work for the research fields of semantic relatedness, named entity recognition, word sense disambiguation, named entity disambiguation, novel  ...  A pre-requisite for the semantic relatedness framework however was specification of an entity of interest against which to calculate relatedness scores; for the domain-specific keyword extraction task  ...  The earlier technique like previous approaches in the literature utilises the Wikipedia disambiguation pages for an entity to determine the amount of disambiguation within a particular tweet while at the  ... 
doi:10.1145/2888422.2888449 fatcat:lck3kkxoazcj5powaqhjs6epty

Enabling social WEB for IoT inducing ontologies from social tagging

Mohammed Alruqimi, Noura Aknin
2019 International Journal of Informatics and Communication Technology (IJ-ICT)  
Furthermore, the proposed algorithm introduced a simple and effective method for disambiguating tags.  ...  Furthermore, the proposed algorithm introduced a simple and effective method for disambiguating tags.</span>  ...  This paper addressed the problem of how to harvest and exploit embedded semantics in social tagging systems for developing semantic ontologies.  ... 
doi:10.11591/ijict.v8i1.pp19-24 fatcat:6etdtt4syfbkvhdgvoq5cp5r3u

Measuring Semantic Similarity and Relatedness with Distributional and Knowledge-based Approaches

Christoph LOFI
2015 Information and Media Technologies  
This paper provides a survey of different techniques for measuring semantic similarity and relatedness of word pairs.  ...  While word embeddings are not fully understood yet, they show promising results for similarity tasks, and may also be suitable for capturing significantly more complex features like relational similarity  ...  between vectors represents a measure for similarity and relatedness, but that also the difference vectors between a word pair carries meaningful semantics [34] .  ... 
doi:10.11185/imt.10.493 fatcat:emuwh4pianaidnuib6fwd2jxlm

Automated product taxonomy mapping in an e-commerce environment

Steven S. Aanen, Damir Vandic, Flavius Frasincar
2015 Expert systems with applications  
The algorithm uses word sense disambiguation techniques to address varying denominations between different taxonomies.  ...  Path similarity is assessed between source and candidate target categories, based on lexical relatedness and structural information.  ...  These semantics describe for example the relations between different products.  ... 
doi:10.1016/j.eswa.2014.09.032 fatcat:byb734n7m5c4fbc32daes5htuy
« Previous Showing results 1 — 15 out of 504 results