@inproceedings{nicosia-piccinno-2022-byte,
title = "Byte-Level Massively Multilingual Semantic Parsing",
author = "Nicosia, Massimo and
Piccinno, Francesco",
editor = "FitzGerald, Jack and
Rottmann, Kay and
Hirschberg, Julia and
Bansal, Mohit and
Rumshisky, Anna and
Peris, Charith and
Hench, Christopher",
booktitle = "Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mmnlu-1.3",
doi = "10.18653/v1/2022.mmnlu-1.3",
pages = "25--34",
abstract = "Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we evaluate a byte-level sequence to sequence model (ByT5) on the 51 languages in the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match to only 5 points with respect to a model trained on gold data from all the languages. We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nicosia-piccinno-2022-byte">
<titleInfo>
<title>Byte-Level Massively Multilingual Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Nicosia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Piccinno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">FitzGerald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kay</namePart>
<namePart type="family">Rottmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hirschberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charith</namePart>
<namePart type="family">Peris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Hench</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we evaluate a byte-level sequence to sequence model (ByT5) on the 51 languages in the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match to only 5 points with respect to a model trained on gold data from all the languages. We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes.</abstract>
<identifier type="citekey">nicosia-piccinno-2022-byte</identifier>
<identifier type="doi">10.18653/v1/2022.mmnlu-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.mmnlu-1.3</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>25</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Byte-Level Massively Multilingual Semantic Parsing
%A Nicosia, Massimo
%A Piccinno, Francesco
%Y FitzGerald, Jack
%Y Rottmann, Kay
%Y Hirschberg, Julia
%Y Bansal, Mohit
%Y Rumshisky, Anna
%Y Peris, Charith
%Y Hench, Christopher
%S Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F nicosia-piccinno-2022-byte
%X Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we evaluate a byte-level sequence to sequence model (ByT5) on the 51 languages in the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match to only 5 points with respect to a model trained on gold data from all the languages. We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes.
%R 10.18653/v1/2022.mmnlu-1.3
%U https://aclanthology.org/2022.mmnlu-1.3
%U https://doi.org/10.18653/v1/2022.mmnlu-1.3
%P 25-34
Markdown (Informal)
[Byte-Level Massively Multilingual Semantic Parsing](https://aclanthology.org/2022.mmnlu-1.3) (Nicosia & Piccinno, MMNLU 2022)
ACL
- Massimo Nicosia and Francesco Piccinno. 2022. Byte-Level Massively Multilingual Semantic Parsing. In Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22), pages 25–34, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.