@inproceedings{goot-2023-machamp,
title = "{M}a{C}h{A}mp at {S}em{E}val-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.",
author = "van der Goot, Rob",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.32",
doi = "10.18653/v1/2023.semeval-1.32",
pages = "230--245",
abstract = "To improve the ability of language models to handle Natural Language Processing(NLP) tasks and intermediate step of pre-training has recently beenintroduced. In this setup, one takes a pre-trained language model, trains it ona (set of) NLP dataset(s), and then finetunes it for a target task. It isknown that the selection of relevant transfer tasks is important, but recentlysome work has shown substantial performance gains by doing intermediatetraining on a very large set of datasets. Most previous work uses generativelanguage models or only focuses on one or a couple of tasks and uses acarefully curated setup. We compare intermediate training with one or manytasks in a setup where the choice of datasets is more arbitrary; we use allSemEval 2023 text-based tasks. We reach performance improvements for most taskswhen using intermediate training. Gains are higher when doing intermediatetraining on single tasks than all tasks if the right transfer taskis identified. Dataset smoothing and heterogeneous batching did not lead torobust gains in our setup.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goot-2023-machamp">
<titleInfo>
<title>MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To improve the ability of language models to handle Natural Language Processing(NLP) tasks and intermediate step of pre-training has recently beenintroduced. In this setup, one takes a pre-trained language model, trains it ona (set of) NLP dataset(s), and then finetunes it for a target task. It isknown that the selection of relevant transfer tasks is important, but recentlysome work has shown substantial performance gains by doing intermediatetraining on a very large set of datasets. Most previous work uses generativelanguage models or only focuses on one or a couple of tasks and uses acarefully curated setup. We compare intermediate training with one or manytasks in a setup where the choice of datasets is more arbitrary; we use allSemEval 2023 text-based tasks. We reach performance improvements for most taskswhen using intermediate training. Gains are higher when doing intermediatetraining on single tasks than all tasks if the right transfer taskis identified. Dataset smoothing and heterogeneous batching did not lead torobust gains in our setup.</abstract>
<identifier type="citekey">goot-2023-machamp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.32</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.32</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>230</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.
%A van der Goot, Rob
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F goot-2023-machamp
%X To improve the ability of language models to handle Natural Language Processing(NLP) tasks and intermediate step of pre-training has recently beenintroduced. In this setup, one takes a pre-trained language model, trains it ona (set of) NLP dataset(s), and then finetunes it for a target task. It isknown that the selection of relevant transfer tasks is important, but recentlysome work has shown substantial performance gains by doing intermediatetraining on a very large set of datasets. Most previous work uses generativelanguage models or only focuses on one or a couple of tasks and uses acarefully curated setup. We compare intermediate training with one or manytasks in a setup where the choice of datasets is more arbitrary; we use allSemEval 2023 text-based tasks. We reach performance improvements for most taskswhen using intermediate training. Gains are higher when doing intermediatetraining on single tasks than all tasks if the right transfer taskis identified. Dataset smoothing and heterogeneous batching did not lead torobust gains in our setup.
%R 10.18653/v1/2023.semeval-1.32
%U https://aclanthology.org/2023.semeval-1.32
%U https://doi.org/10.18653/v1/2023.semeval-1.32
%P 230-245
Markdown (Informal)
[MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.](https://aclanthology.org/2023.semeval-1.32) (van der Goot, SemEval 2023)
- MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets. (van der Goot, SemEval 2023)
ACL
- Rob van der Goot. 2023. MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 230–245, Toronto, Canada. Association for Computational Linguistics.