@inproceedings{lindemann-etal-2023-compositional,
title = "Compositional Generalisation with Structured Reordering and Fertility Layers",
author = "Lindemann, Matthias and
Koller, Alexander and
Titov, Ivan",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.159",
doi = "10.18653/v1/2023.eacl-main.159",
pages = "2172--2186",
abstract = "Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at compositional generalisation, we present a flexible end-to-end differentiable neural model that composes two structural operations: a fertility step, which we introduce in this work, and a reordering step based on previous work (Wang et al., 2021). To ensure differentiability, we use the expected value of each step, which we compute using dynamic programming. Our model outperforms seq2seq models by a wide margin on challenging compositional splits of realistic semantic parsing tasks that require generalisation to longer examples. It also compares favourably to other models targeting compositional generalisation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lindemann-etal-2023-compositional">
<titleInfo>
<title>Compositional Generalisation with Structured Reordering and Fertility Layers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Lindemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Titov</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 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</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>Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at compositional generalisation, we present a flexible end-to-end differentiable neural model that composes two structural operations: a fertility step, which we introduce in this work, and a reordering step based on previous work (Wang et al., 2021). To ensure differentiability, we use the expected value of each step, which we compute using dynamic programming. Our model outperforms seq2seq models by a wide margin on challenging compositional splits of realistic semantic parsing tasks that require generalisation to longer examples. It also compares favourably to other models targeting compositional generalisation.</abstract>
<identifier type="citekey">lindemann-etal-2023-compositional</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.159</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.159</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>2172</start>
<end>2186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compositional Generalisation with Structured Reordering and Fertility Layers
%A Lindemann, Matthias
%A Koller, Alexander
%A Titov, Ivan
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F lindemann-etal-2023-compositional
%X Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at compositional generalisation, we present a flexible end-to-end differentiable neural model that composes two structural operations: a fertility step, which we introduce in this work, and a reordering step based on previous work (Wang et al., 2021). To ensure differentiability, we use the expected value of each step, which we compute using dynamic programming. Our model outperforms seq2seq models by a wide margin on challenging compositional splits of realistic semantic parsing tasks that require generalisation to longer examples. It also compares favourably to other models targeting compositional generalisation.
%R 10.18653/v1/2023.eacl-main.159
%U https://aclanthology.org/2023.eacl-main.159
%U https://doi.org/10.18653/v1/2023.eacl-main.159
%P 2172-2186
Markdown (Informal)
[Compositional Generalisation with Structured Reordering and Fertility Layers](https://aclanthology.org/2023.eacl-main.159) (Lindemann et al., EACL 2023)
ACL