DE eng

Search in the Catalogues and Directories

Hits 1 – 10 of 10

1
Probing for idiomaticity in vector space models
Garcia, M.; Vieira, T.K.; Scarton, C.. - : Association for Computational Linguistics (ACL), 2021
BASE
Show details
2
Unsupervised compositionality prediction of nominal compounds
Cordeiro, S.; Villavicencio, A.; Idiart, M.. - : MIT Press - Journals, 2019
BASE
Show details
3
Discovering multiword expressions
Villavicencio, A.; Idiart, M.. - : Cambridge University Press (CUP), 2019
BASE
Show details
4
Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks
Paula, F.; Wilkens, R.; Idiart, M.. - : Association for Computational Linguistics, 2018
BASE
Show details
5
How naked is the naked truth? A multilingual lexicon of nominal compound compositionality
Villavicencio, A.; Wilkens, R.; Ramisch, C.. - : Association for Computational Linguistics, 2016
BASE
Show details
6
Multiword expressions in child language
Wilkens, R.; Idiart, M.; Villavicencio, A.. - : European Language Resources Association (ELRA), 2016
BASE
Show details
7
Predicting the compositionality of nominal compounds: Giving word embeddings a hard time
Cordeiro, S.; Ramisch, C.; Idiart, M.; Villavicencio, A.. - : Association for Computational Linguistics, 2016
Abstract: Distributional semantic models (DSMs) are often evaluated on artificial similarity datasets containing single words or fully compositional phrases. We present a large-scale multilingual evaluation of DSMs for predicting the degree of semantic compositionality of nominal compounds on 4 datasets for English and French. We build a total of 816 DSMs and perform 2,856 evaluations using word2vec, GloVe, and PPMI-based models. In addition to the DSMs, we compare the impact of different parameters, such as level of corpus preprocessing, context window size and number of dimensions. The results obtained have a high correlation with human judgments, being comparable to or outperforming the state of the art for some datasets (Spearman's ρ=.82 for the Reddy dataset).
URL: http://eprints.whiterose.ac.uk/153562/
BASE
Hide details
8
Matrix factorization using window sampling and negative sampling for improved word representations
Salle, A.; Idiart, M.; Villavicencio, A.. - : Association for Computational Linguistics, 2016
BASE
Show details
9
Nothing like good old frequency: Studying context filters for distributional thesauri
Padró, M.; Idiart, M.; Ramisch, C.. - : Association for Computational Linguistics, 2014
BASE
Show details
10
Language acquisition and probabilistic models : keeping it simple
Villavicencio, A.; Malioutov, I.; Idiart, M.. - : Association for Computational Linguistics (ACL), 2013
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
10
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern