Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/81633
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Chinese and Bilingual Studies | en_US |
dc.creator | Liu, H | en_US |
dc.creator | Chersoni, E | en_US |
dc.creator | Klyueva, N | en_US |
dc.creator | Santus, E | en_US |
dc.creator | Huang, CR | en_US |
dc.date.accessioned | 2020-01-21T08:49:18Z | - |
dc.date.available | 2020-01-21T08:49:18Z | - |
dc.identifier.issn | 2169-3536 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/81633 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/ | en_US |
dc.rights | The following publication Liu, H., Chersoni, E., Klyueva, N., Santus, E., & Huang, C. R. (2019). Semantic Relata for the Evaluation of Distributional Models in Mandarin Chinese. IEEE Access, 7, 145705-145713 is available at https://doi.org/10.1109/ACCESS.2019.2945061 | en_US |
dc.subject | Computational semantics | en_US |
dc.subject | Lexical resources | en_US |
dc.subject | Ontologies | en_US |
dc.subject | Relation classification | en_US |
dc.subject | Semantic relations | en_US |
dc.subject | Vector space models | en_US |
dc.title | Semantic relata for the evaluation of distributional models in Mandarin Chinese | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 145705 | en_US |
dc.identifier.epage | 145713 | en_US |
dc.identifier.volume | 7 | en_US |
dc.identifier.doi | 10.1109/ACCESS.2019.2945061 | en_US |
dcterms.abstract | Distributional Semantic Models (DSMs) established themselves as a standard for the representation of word and sentence meaning. However, DSMs provide quantitative measurement of how strongly two linguistic expressions are related, without being able to automatically classify different semantic relations. Hence the notion of semantic similarity is underspecified in DSMs. We introduce Evalution-MAN in this paper as an effort to address this underspecification problem. Following the EVALution 1.0 dataset for English, we present a dataset for evaluating DSMs on the task of the identification of semantic relations in Mandarin Chinese. Moreover, we test different types of word vectors on the automatic learning of these semantic relations, and we evaluate them both in a unsupervised and in a supervised setting, finding that distributional models tend, in general, to assign higher similarity scores to synonyms and that deep learning classifiers are the best performing ones in the identification of semantic relations. | en_US |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE access, 2019, 8854798, p. 145705-145713 | en_US |
dcterms.isPartOf | IEEE access | en_US |
dcterms.issued | 2019 | - |
dc.identifier.isi | WOS:000498818400001 | - |
dc.identifier.scopus | 2-s2.0-85073609627 | - |
dc.description.validate | 202001 bcma | en_US |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | a0670-n12, OA_Scopus/WOS | en_US |
dc.description.pubStatus | Published | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Liu_Semantic_relata_evaluation.pdf | 7.21 MB | Adobe PDF | View/Open |
Page views
130
Last Week
1
1
Last month
Citations as of Apr 21, 2024
Downloads
67
Citations as of Apr 21, 2024
SCOPUSTM
Citations
3
Citations as of Apr 19, 2024
WEB OF SCIENCETM
Citations
1
Citations as of Apr 25, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.