@inproceedings{goot-2022-machamp,
title = "{M}a{C}h{A}mp at {S}em{E}val-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets",
author = "van der Goot, Rob",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.233/",
doi = "10.18653/v1/2022.semeval-1.233",
pages = "1695--1703",
abstract = "Previous work on multi-task learning in Natural Language Processing (NLP) oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share information across tasks. Recently, it has shown thatfor autoregressive language models, a multi-task second pre-training step on awide variety of NLP tasks leads to a set of parameters that more easily adaptfor other NLP tasks. In this paper, we examine whether a similar setup can beused in autoencoder language models using a restricted set of semanticallyoriented NLP tasks, namely all SemEval 2022 tasks that are annotated at theword, sentence or paragraph level. We first evaluate a multi-task model trainedon all SemEval 2022 tasks that contain annotation on the word, sentence orparagraph level (7 tasks, 11 sub-tasks), and then evaluate whetherre-finetuning the resulting model for each task specificially leads to furtherimprovements. Our results show that our mono-task baseline, our multi-taskmodel and our re-finetuned multi-task model each outperform the other modelsfor a subset of the tasks. Overall, huge gains can be observed by doingmulti-task learning: for three tasks we observe an error reduction of more than40{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goot-2022-machamp">
<titleInfo>
<title>MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic 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>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</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">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work on multi-task learning in Natural Language Processing (NLP) oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share information across tasks. Recently, it has shown thatfor autoregressive language models, a multi-task second pre-training step on awide variety of NLP tasks leads to a set of parameters that more easily adaptfor other NLP tasks. In this paper, we examine whether a similar setup can beused in autoencoder language models using a restricted set of semanticallyoriented NLP tasks, namely all SemEval 2022 tasks that are annotated at theword, sentence or paragraph level. We first evaluate a multi-task model trainedon all SemEval 2022 tasks that contain annotation on the word, sentence orparagraph level (7 tasks, 11 sub-tasks), and then evaluate whetherre-finetuning the resulting model for each task specificially leads to furtherimprovements. Our results show that our mono-task baseline, our multi-taskmodel and our re-finetuned multi-task model each outperform the other modelsfor a subset of the tasks. Overall, huge gains can be observed by doingmulti-task learning: for three tasks we observe an error reduction of more than40%.</abstract>
<identifier type="citekey">goot-2022-machamp</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.233</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.233/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1695</start>
<end>1703</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets
%A van der Goot, Rob
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F goot-2022-machamp
%X Previous work on multi-task learning in Natural Language Processing (NLP) oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share information across tasks. Recently, it has shown thatfor autoregressive language models, a multi-task second pre-training step on awide variety of NLP tasks leads to a set of parameters that more easily adaptfor other NLP tasks. In this paper, we examine whether a similar setup can beused in autoencoder language models using a restricted set of semanticallyoriented NLP tasks, namely all SemEval 2022 tasks that are annotated at theword, sentence or paragraph level. We first evaluate a multi-task model trainedon all SemEval 2022 tasks that contain annotation on the word, sentence orparagraph level (7 tasks, 11 sub-tasks), and then evaluate whetherre-finetuning the resulting model for each task specificially leads to furtherimprovements. Our results show that our mono-task baseline, our multi-taskmodel and our re-finetuned multi-task model each outperform the other modelsfor a subset of the tasks. Overall, huge gains can be observed by doingmulti-task learning: for three tasks we observe an error reduction of more than40%.
%R 10.18653/v1/2022.semeval-1.233
%U https://aclanthology.org/2022.semeval-1.233/
%U https://doi.org/10.18653/v1/2022.semeval-1.233
%P 1695-1703
Markdown (Informal)
[MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets](https://aclanthology.org/2022.semeval-1.233/) (van der Goot, SemEval 2022)
ACL