@inproceedings{stefanik-etal-2023-resources,
title = "Resources and Few-shot Learners for In-context Learning in {S}lavic Languages",
author = "{\v{S}}tef{\'a}nik, Michal and
Kadl{\v{c}}{\'\i}k, Marek and
Gramacki, Piotr and
Sojka, Petr",
editor = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Ogrodniczuk, Maciej and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Rybak, Piotr and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bsnlp-1.12",
doi = "10.18653/v1/2023.bsnlp-1.12",
pages = "94--105",
abstract = "Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stefanik-etal-2023-resources">
<titleInfo>
<title>Resources and Few-shot Learners for In-context Learning in Slavic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Štefánik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Kadlčík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Gramacki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Sojka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.</abstract>
<identifier type="citekey">stefanik-etal-2023-resources</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.12</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>94</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resources and Few-shot Learners for In-context Learning in Slavic Languages
%A Štefánik, Michal
%A Kadlčík, Marek
%A Gramacki, Piotr
%A Sojka, Petr
%Y Piskorski, Jakub
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Ogrodniczuk, Maciej
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Rybak, Piotr
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F stefanik-etal-2023-resources
%X Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.
%R 10.18653/v1/2023.bsnlp-1.12
%U https://aclanthology.org/2023.bsnlp-1.12
%U https://doi.org/10.18653/v1/2023.bsnlp-1.12
%P 94-105
Markdown (Informal)
[Resources and Few-shot Learners for In-context Learning in Slavic Languages](https://aclanthology.org/2023.bsnlp-1.12) (Štefánik et al., BSNLP 2023)
ACL