TY - GEN
T1 - Assessing wordnets with WordNet embeddings
AU - Branco, Ruben
AU - Rodrigues, João
AU - Saedi, Chakaveh
AU - Branco, António
N1 - Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2019
Y1 - 2019
N2 - An effective conversion method was proposed in the literature to obtain a lexical semantic space from a lexical semantic graph, thus permitting to obtain WordNet embeddings from WordNets. In this paper, we propose the exploitation of this conversion methodology as the basis for the comparative assessment of WordNets: given two WordNets, their relative quality in terms of capturing the lexical semantics of a given language, can be assessed by (i) converting each WordNet into the corresponding semantic space (i.e. into WordNet embeddings), (ii) evaluating the resulting WordNet embeddings under the typical semantic similarity prediction task used to evaluate word embeddings in general; and (iii) comparing the performance in that task of the two word embeddings, extracted from the two WordNets. A better performance in that evaluation task results from the word embeddings that are better at capturing the semantic similarity of words, which, in turn, result from the WordNet that is of higher quality at capturing the semantics of words.
AB - An effective conversion method was proposed in the literature to obtain a lexical semantic space from a lexical semantic graph, thus permitting to obtain WordNet embeddings from WordNets. In this paper, we propose the exploitation of this conversion methodology as the basis for the comparative assessment of WordNets: given two WordNets, their relative quality in terms of capturing the lexical semantics of a given language, can be assessed by (i) converting each WordNet into the corresponding semantic space (i.e. into WordNet embeddings), (ii) evaluating the resulting WordNet embeddings under the typical semantic similarity prediction task used to evaluate word embeddings in general; and (iii) comparing the performance in that task of the two word embeddings, extracted from the two WordNets. A better performance in that evaluation task results from the word embeddings that are better at capturing the semantic similarity of words, which, in turn, result from the WordNet that is of higher quality at capturing the semantics of words.
UR - http://www.scopus.com/inward/record.url?scp=85082461594&partnerID=8YFLogxK
M3 - Conference proceeding contribution
AN - SCOPUS:85082461594
T3 - Proceedings of the 10th Global WordNet Conference
SP - 253
EP - 259
BT - Proceedings of the 10th Global WordNet Conference
A2 - Fellbaum, Christiane
A2 - Vossen, Piek
A2 - Rudnicka, Ewa
A2 - Maziarz, Marek
A2 - Piasecki, Maciej
PB - Global Wordnet Association
CY - Wroclaw
T2 - 10th Global WordNet Conference, GWC 2019
Y2 - 23 July 2019 through 27 July 2019
ER -