Results 11 to 20 of about 7,167 (213)

Large-scale image annotation using visual synset

open access: green2011 International Conference on Computer Vision, 2011
We address the problem of large-scale annotation of web images. Our approach is based on the concept of visual synset, which is an organization of images which are visually-similar and semantically-related. Each visual synset represents a single prototypical visual concept, and has an associated set of weighted annotations. Linear SVM's are utilized to
David Tsai   +5 more
semanticscholar   +4 more sources

Improving Performance of NMT Using Semantic Concept of WordNet Synset

open access: diamondEasyChair Preprints, 2018
Neural machine translation (NMT) has shown promising progress in recent years. However, for reducing the computational complexity, NMT typically needs to limit its vocabulary scale to a fixed or relatively acceptable size, which leads to the problem of ...
Fangxu Liu   +4 more
semanticscholar   +5 more sources

Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings [PDF]

open access: greenSEALP, 2022
Wordnets are indispensable tools for various natural language processing applications. Unfortunately, wordnets get outdated, and producing or updating wordnets can be slow and costly in terms of time and resources.
Dan John Velasco   +7 more
semanticscholar   +3 more sources

Exploiting WordNet Synset and Hypernym Representations for Answer Selection [PDF]

open access: goldAACL, 2020
Answer selection (AS) is an important subtask of document-based question answering (DQA). In this task, the candidate answers come from the same document, and each answer sentence is semantically related to the given question, which makes it more ...
W. Li, Yunfang Wu
semanticscholar   +2 more sources

Linking ImageNet WordNet Synsets with Wikidata [PDF]

open access: goldCompanion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018
6 pages, Wiki Workshop ...
Finn Årup Nielsen
openalex   +3 more sources

Fighting with the Sparsity of Synonymy Dictionaries [PDF]

open access: yesInternational Joint Conference on the Analysis of Images, Social Networks and Texts, 2017
Graph-based synset induction methods, such as MaxMax and Watset, induce synsets by performing a global clustering of a synonymy graph. However, such methods are sensitive to the structure of the input synonymy graph: sparseness of the input dictionary ...
A Panchenko   +8 more
core   +3 more sources

Improving the Precision of Synset Links Between Cornetto and Princeton WordNet [PDF]

open access: goldLG-LP@COLING, 2014
Knowledge-based multilingual language processing benefits from having access to correctly established relations between semantic lexicons, such as the links between different WordNets.
L. Sevens   +2 more
semanticscholar   +2 more sources

The natural selection of words: Finding the features of fitness. [PDF]

open access: yesPLoS ONE, 2019
We introduce a dataset for studying the evolution of words, constructed from WordNet and the Google Books Ngram Corpus. The dataset tracks the evolution of 4,000 synonym sets (synsets), containing 9,000 English words, from 1800 AD to 2000 AD.
Peter D Turney, Saif M Mohammad
doaj   +2 more sources

Multi-Modal Word Synset Induction

open access: yesProceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017
A word in natural language can be polysemous, having multiple meanings, as well as synonymous, meaning the same thing as other words. Word sense induction attempts to find the senses of polysemous words. Synonymy detection attempts to find when two words are interchangeable.
Jesse Thomason, R. Mooney
semanticscholar   +2 more sources

Data-driven synset induction and disambiguation for wordnet development [PDF]

open access: yesLanguage Resources and Evaluation, 2014
Automatic methods for wordnet development in languages other than English generally exploit information found in Princeton WordNet (PWN) and translations extracted from parallel corpora. A common approach consists in preserving the structure of PWN and transferring its content in new languages using alignments, possibly combined with information ...
Marianna Apidianaki, Benoît Sagot
semanticscholar   +2 more sources

Home - About - Disclaimer - Privacy