From web to dialects: how to enhance non-standard Russian lects lemmatisation?
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AUBLWDWCL" target="_blank" >RIV/00216208:11320/23:UBLWDWCL - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2023.clasp-1.17/" target="_blank" >https://aclanthology.org/2023.clasp-1.17/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
From web to dialects: how to enhance non-standard Russian lects lemmatisation?
Original language description
"The growing need for using small data distinguished by a set of distributional properties becomes all the more apparent in the era of large language models (LLM). In this paper, we show that for the lemmatisation of the web as corpora texts, heterogeneous social media texts, and dialect texts, the morphological tagging by a model trained on a small dataset with specific properties generally works better than the morphological tagging by a model trained on a large dataset. The material we use is Russian non-standard texts and interviews with dialect speakers. The sequence-to-sequence lemmatisation with the help of taggers trained on smaller linguistically aware datasets achieves the average results of 85 to 90 per cent. These results are consistently (but not always), by 1-2 per cent. higher than the results of lemmatisation with the help of the large-dataset-trained taggers. We analyse these results and outline the possible further research directions."
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
"Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)"
ISBN
979-8-89176-000-4
ISSN
2002-9764
e-ISSN
—
Number of pages
9
Pages from-to
167-175
Publisher name
Association for Computational Linguistics
Place of publication
Gothenburg, Sweden
Event location
Gothenburg, Sweden
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—