1 |
Multi-sense embeddings through a word sense disambiguation process ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Enhanced word embeddings using multi-semantic representation through lexical chains ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Enhanced word embeddings using multi-semantic representation through lexical chains ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Semantic Feature Extraction Using Multi-Sense Embeddings and Lexical Chains
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Multi-sense Embeddings through a Word Sense Disambiguation Process
|
|
|
|
Abstract:
Natural Language Understanding has seen an increasing number of publications in the last years, especially after robust word embedding models became popular. These models gained a special place in the spotlight when they proved themselves able to capture and represent semantic relations underneath huge amounts of data. Nevertheless, traditional models often fall short in intrinsic issues of linguistics, such as polysemy and homonymy. Multi-sense word embeddings were devised to alleviate these and other problems by representing each word-sense separately, but studies in this area are still in its infancy and much can be explored. We follow this scenario by proposing an unsupervised technique that disambiguates and annotates words by their specific sense, considering their context influence. These are later used to train a word embeddings model to produce a more accurate vector representation. We test our approach in 6 different benchmarks for the word similarity task, showing that our approach can sustain good results and often outperforms current state-of-the-art systems. ; https://deepblue.lib.umich.edu/bitstream/2027.42/145475/3/tacl.pdf ; Description of tacl.pdf : WorkingPaper
|
|
Keyword:
Computer Science; Engineering; word similarity; Word2vec; wordnet; wsd
|
|
URL: https://hdl.handle.net/2027.42/145475
|
|
BASE
|
|
Hide details
|
|
6 |
Database and Expert Systems Applications - 28th International Conference, DEXA 2017, Lyon, France, Proceedings part II
|
|
|
|
In: ISSN: 0302-9743 ; Lecture Notes in Computer Science ; 28th International Conference on Database and Expert Systems Applications and Workshops (DEXA 2017) ; https://hal.archives-ouvertes.fr/hal-03120290 ; Benslimane, Djamal; Damiani, Ernesto; Grosky, William I.; Hameurlain, Abdelkader; Sheth, Amit P.; Wagner, Roland R. 28th International Conference on Database and Expert Systems Applications and Workshops (DEXA 2017), Aug 2017, Lyon, France. Lecture Notes in Computer Science, 10439 (Part II), Springer, 2017, Database and Expert Systems Applications 28th International Conference, DEXA 2017, Lyon, France, 978-3-319-64470-7. ⟨10.1007/978-3-319-64471-4⟩ ; https://link.springer.com/book/10.1007%2F978-3-319-64471-4 (2017)
|
|
BASE
|
|
Show details
|
|
7 |
Database and Expert Systems Applications - 28th International Conference, DEXA 2017, Lyon, France, Proceedings part I
|
|
|
|
In: ISSN: 0302-9743 ; Lecture Notes in Computer Science ; 28th International Conference on Database and Expert Systems Applications and Workshops (DEXA 2017) ; https://hal.archives-ouvertes.fr/hal-03120283 ; Benslimane, Djamal; Damiani, Ernesto; Grosky, William I.; Hameurlain, Abdelkader; Amit P., Sheth; Wagner, Roland. 28th International Conference on Database and Expert Systems Applications and Workshops (DEXA 2017), Aug 2017, Lyon, France. Lecture Notes in Computer Science, 10438, Springer, 517 p., 2017, Lecture Notes in Computer Science book series (LNCS), 978-3-319-64467-7 ; https://link.springer.com/book/10.1007%2F978-3-319-64468-4 (2017)
|
|
BASE
|
|
Show details
|
|
8 |
Semantic-Based Document Retrieval Using Spatial Distributions of Concepts ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Exploring and Expanding the Use of Lexical Chains in Information Retrieval
|
|
|
|
BASE
|
|
Show details
|
|
|
|