Exploring Word Composition Knowledge in Language Usages
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A3CZAUS8F" target="_blank" >RIV/00216208:11320/25:3CZAUS8F - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85206220327&doi=10.1007%2f978-981-97-5501-1_5&partnerID=40&md5=2ba8c71ef813de335fc48f1749f9809d" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85206220327&doi=10.1007%2f978-981-97-5501-1_5&partnerID=40&md5=2ba8c71ef813de335fc48f1749f9809d</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-981-97-5501-1_5" target="_blank" >10.1007/978-981-97-5501-1_5</a>
Alternative languages
Result language
angličtina
Original language name
Exploring Word Composition Knowledge in Language Usages
Original language description
The creativity of language is a distinct feature that sets humans apart from machines and animals, where the flexibility of word composition is the fundamental part. The patterns on words that are systematically linked together are acknowledged as the word composition knowledge. We explore this knowledge by combining the syntax information with word semantics and verify it through a series of empirical experiments on multiple datasets. From the linguistic perspective, we found that this knowledge can find the appropriate alternatives for the given phrase and generate high-quality paraphrases that satisfy both the syntax soundness and the semantic consistency with the original text. We also verify it on the questionnaires in psychological testing and find the abnormal patterns on the language usages. Compared to the large pre-trained models, this method is much more training-economic and can generate the paraphrases in an explainable way. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lect. Notes Comput. Sci.
ISBN
978-981975500-4
ISSN
0302-9743
e-ISSN
—
Number of pages
12
Pages from-to
61-72
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
—
Event location
Birmingham
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—