@inproceedings{levy-etal-2023-diverse,
title = "Diverse Demonstrations Improve In-context Compositional Generalization",
author = "Levy, Itay and
Bogin, Ben and
Berant, Jonathan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.78",
doi = "10.18653/v1/2023.acl-long.78",
pages = "1401--1422",
abstract = "In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the input utterance. However, in the setup of compositional generalization, where models are tested on outputs with structures that are absent from the training set, selecting similar demonstrations is insufficient, as often no example will be similar enough to the input. In this work, we propose a method to select diverse demonstrations that aims to collectively cover all of the structures required in the output program, in order to encourage the model to generalize to new structures from these demonstrations. We empirically show that combining diverse demonstrations with in-context learning substantially improves performance across three compositional generalization semantic parsing datasets in the pure in-context learning setup and when combined with finetuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="levy-etal-2023-diverse">
<titleInfo>
<title>Diverse Demonstrations Improve In-context Compositional Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Bogin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the input utterance. However, in the setup of compositional generalization, where models are tested on outputs with structures that are absent from the training set, selecting similar demonstrations is insufficient, as often no example will be similar enough to the input. In this work, we propose a method to select diverse demonstrations that aims to collectively cover all of the structures required in the output program, in order to encourage the model to generalize to new structures from these demonstrations. We empirically show that combining diverse demonstrations with in-context learning substantially improves performance across three compositional generalization semantic parsing datasets in the pure in-context learning setup and when combined with finetuning.</abstract>
<identifier type="citekey">levy-etal-2023-diverse</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.78</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.78</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1401</start>
<end>1422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diverse Demonstrations Improve In-context Compositional Generalization
%A Levy, Itay
%A Bogin, Ben
%A Berant, Jonathan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F levy-etal-2023-diverse
%X In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the input utterance. However, in the setup of compositional generalization, where models are tested on outputs with structures that are absent from the training set, selecting similar demonstrations is insufficient, as often no example will be similar enough to the input. In this work, we propose a method to select diverse demonstrations that aims to collectively cover all of the structures required in the output program, in order to encourage the model to generalize to new structures from these demonstrations. We empirically show that combining diverse demonstrations with in-context learning substantially improves performance across three compositional generalization semantic parsing datasets in the pure in-context learning setup and when combined with finetuning.
%R 10.18653/v1/2023.acl-long.78
%U https://aclanthology.org/2023.acl-long.78
%U https://doi.org/10.18653/v1/2023.acl-long.78
%P 1401-1422
Markdown (Informal)
[Diverse Demonstrations Improve In-context Compositional Generalization](https://aclanthology.org/2023.acl-long.78) (Levy et al., ACL 2023)
ACL