Cross-Framework Evaluation for Portuguese POS Taggers and Parsers
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AMTPIXMV9" target="_blank" >RIV/00216208:11320/23:MTPIXMV9 - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149994739&doi=10.1007%2f978-3-031-23804-8_16&partnerID=40&md5=a6616f5a79174b0710d41c5f1f96886f" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149994739&doi=10.1007%2f978-3-031-23804-8_16&partnerID=40&md5=a6616f5a79174b0710d41c5f1f96886f</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-23804-8_16" target="_blank" >10.1007/978-3-031-23804-8_16</a>
Alternative languages
Result language
angličtina
Original language name
Cross-Framework Evaluation for Portuguese POS Taggers and Parsers
Original language description
"This work compares POS and parsing systems for the Portuguese language. We analyse available features, tagsets, and compare the results of POS tagging, and syntactic structure identification by means of both intrinsic and extrinsic evaluation methods. For such, we use in this work well-known metric for parser evaluation such as bracket cross, leaf ancestor for intrinsic evaluation, as well as the application of such parsers to the task of noun phrase identification, for extrinsic evaluation. The comparison proposed in this work takes into account the different linguistic theories and frameworks each parser subscribes to, but it is not dependent of any particular one. © 2023, Springer Nature Switzerland AG."
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
2023
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
978-303123803-1
ISSN
0302-9743
e-ISSN
—
Number of pages
12
Pages from-to
197-208
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
—
Event location
Singapore
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—