Prompt-Based Approach for Czech Sentiment Analysis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F23%3A43970187" target="_blank" >RIV/49777513:23520/23:43970187 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.26615/978-954-452-092-2_118" target="_blank" >https://doi.org/10.26615/978-954-452-092-2_118</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.26615/978-954-452-092-2_118" target="_blank" >10.26615/978-954-452-092-2_118</a>
Alternative languages
Result language
angličtina
Original language name
Prompt-Based Approach for Czech Sentiment Analysis
Original language description
This paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech. We employ the sequence-to-sequence models to solve the aspect-based tasks simultaneously and demonstrate the superiority of our prompt-based approach over traditional fine-tuning. In addition, we conduct zero-shot and few-shot learning experiments for sentiment classification and show that prompting yields significantly better results with limited training examples compared to traditional fine-tuning. We also demonstrate that pre-training on data from the target domain can lead to significant improvements in a zero-shot scenario.
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
S - Specificky vyzkum na vysokych skolach
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
Large Language Models for Natural Language Processing
ISBN
978-954-452-092-2
ISSN
1313-8502
e-ISSN
2603-2813
Number of pages
11
Pages from-to
1110-1120
Publisher name
INCOMA Ltd.
Place of publication
Shoumen
Event location
Varna
Event date
Sep 4, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—