@inproceedings{afanasev-lyashevskaya-2023-web,
title = "From web to dialects: how to enhance non-standard {R}ussian lects lemmatisation?",
author = "Afanasev, Ilia and
Lyashevskaya, Olga",
editor = "Breitholtz, Ellen and
Lappin, Shalom and
Loaiciga, Sharid and
Ilinykh, Nikolai and
Dobnik, Simon",
booktitle = "Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)",
month = sep,
year = "2023",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clasp-1.17",
pages = "167--175",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afanasev-lyashevskaya-2023-web">
<titleInfo>
<title>From web to dialects: how to enhance non-standard Russian lects lemmatisation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilia</namePart>
<namePart type="family">Afanasev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Lyashevskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shalom</namePart>
<namePart type="family">Lappin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">afanasev-lyashevskaya-2023-web</identifier>
<location>
<url>https://aclanthology.org/2023.clasp-1.17</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>167</start>
<end>175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From web to dialects: how to enhance non-standard Russian lects lemmatisation?
%A Afanasev, Ilia
%A Lyashevskaya, Olga
%Y Breitholtz, Ellen
%Y Lappin, Shalom
%Y Loaiciga, Sharid
%Y Ilinykh, Nikolai
%Y Dobnik, Simon
%S Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)
%D 2023
%8 September
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F afanasev-lyashevskaya-2023-web
%X 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.
%U https://aclanthology.org/2023.clasp-1.17
%P 167-175
Markdown (Informal)
[From web to dialects: how to enhance non-standard Russian lects lemmatisation?](https://aclanthology.org/2023.clasp-1.17) (Afanasev & Lyashevskaya, CLASP 2023)
ACL