Building Sense Representations in Danish by Combining Word Embeddings with Lexical Resources
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Building Sense Representations in Danish by Combining Word Embeddings with Lexical Resources. / Olsen, Ida Rørmann; Sayeed, Asad ; Pedersen, Bolette Sandford.
Globalex Workshop on Linked Lexicography: LREC 2020 Workshop Language Resources and Evaluation Conference. Marseille, France : European Language Resources Association, 2020. s. 45-52.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Building Sense Representations in Danish by Combining Word Embeddings with Lexical Resources
AU - Olsen, Ida Rørmann
AU - Sayeed, Asad
AU - Pedersen, Bolette Sandford
PY - 2020
Y1 - 2020
N2 - Our aim is to identify suitable sense representations for NLP in Danish. We investigate sense inventories that correlate with human interpretations of word meaning and ambiguity as typically described in dictionaries and wordnets and that are well reflected distributionallyas expressed in word embeddings. To this end, we study a number of highly ambiguous Danish nouns and examine the effectiveness ofsense representations constructed by combining vectors from a distributional model with the information from a wordnet. We establishrepresentations based on centroids obtained from wordnet synsets and example sentences as well as representations established viaa clustering approach; these representations are tested in a word sense disambiguation task. We conclude that the more informationextracted from the wordnet entries (example sentence, definition, semantic relations) the more successful the sense representation vector.
AB - Our aim is to identify suitable sense representations for NLP in Danish. We investigate sense inventories that correlate with human interpretations of word meaning and ambiguity as typically described in dictionaries and wordnets and that are well reflected distributionallyas expressed in word embeddings. To this end, we study a number of highly ambiguous Danish nouns and examine the effectiveness ofsense representations constructed by combining vectors from a distributional model with the information from a wordnet. We establishrepresentations based on centroids obtained from wordnet synsets and example sentences as well as representations established viaa clustering approach; these representations are tested in a word sense disambiguation task. We conclude that the more informationextracted from the wordnet entries (example sentence, definition, semantic relations) the more successful the sense representation vector.
M3 - Article in proceedings
SP - 45
EP - 52
BT - Globalex Workshop on Linked Lexicography
PB - European Language Resources Association
CY - Marseille, France
ER -
ID: 241359613