Results 51 to 60 of about 46,318 (263)
Journal of the Association for Information Science and Technology, EarlyView.Abstract The term semantic primitives refers to a set of basic, atomic concepts from which all other (compound) concepts are constructed. It presupposes the principle of compositionality—the idea that complex items or expressions can be formed by combining simpler constituents.
Birger Hjørland
wiley +1 more source
Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language [PDF]
Journal of Artificial Intelligence and Data MiningIn the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining, including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper
Farid Ariai +2 more
doaj +1 more source
Extending, trimming and fusing WordNet for technical documents [PDF]
, 2001 This paper describes a tool for the automatic extension and trimming of a multilingual WordNet database for cross-lingual retrieval and multilingual ontology building in intranets and domain-specific document collections.
Vossen, P.
core +2 more sources
Ontology-Aware Token Embeddings for Prepositional Phrase Attachment
, 2017 Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language.
Ammar, Waleed +3 more
core +1 more source
NASARI: a novel approach to a Semantically-Aware Representation of items [PDF]
, 2015 The semantic representation of individual word senses and concepts is of fundamental importance to several applications in Natural Language Processing.
CAMACHO COLLADOS, Jose' +2 more
core +2 more sources
A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches
North American Chapter of the Association for Computational Linguistics, 2009 This paper presents and compares WordNet-based and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented.
Eneko Agirre +5 more
semanticscholar +1 more source
Ai Magazine, 2003 Despite its original intended use, which was very different, WORDNET is used more and more today as an ontology, where the hyponym relation between word senses is interpreted as a subsumption relation between concepts. In this article, we discuss the general problems related to the semantic interpretation of WORDNET taxonomy in light of rigorous ...
Gangemi A +3 more
openaire +6 more sources
Single or Multiple? Combining Word Representations Independently Learned from Text and WordNet
AAAI Conference on Artificial Intelligence, 2016 Text and Knowledge Bases are complementary sources of information. Given the success of distributed word representations learned from text, several techniques to infuse additional information from sources like WordNet into word representations have ...
J. Goikoetxea +2 more
semanticscholar +1 more source
British Journal of Psychology, EarlyView.Abstract Explainable AI (XAI) methods provide explanations of AI models, but our understanding of how they compare with human explanations remains limited. Here, we examined human participants' attention strategies when classifying images and when explaining how they classified the images through eye‐tracking and compared their attention strategies ...
Ruoxi Qi +4 more
wiley +1 more source
Multi-Class Document Classification Using Lexical Ontology-Based Deep Learning
Applied Sciences, 2023 With the recent growth of the Internet, the volume of data has also increased. In particular, the increase in the amount of unstructured data makes it difficult to manage data. Classification is also needed in order to be able to use the data for various
Ilkay Yelmen, Ali Gunes, Metin Zontul
doaj +1 more source