@article{sherborne-etal-2023-optimal,
title = "Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing",
author = "Sherborne, Tom and
Hosking, Tom and
Lapata, Mirella",
journal = "Transactions of the Association for Computational Linguistics",
volume = "11",
year = "2023",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2023.tacl-1.81",
doi = "10.1162/tacl_a_00611",
pages = "1432--1450",
abstract = "Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. Previous work has primarily considered silver-standard data augmentation or zero-shot methods; exploiting few-shot gold data is comparatively unexplored. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between probabilistic latent variables using Optimal Transport. We demonstrate how this direct guidance improves parsing from natural languages using fewer examples and less training. We evaluate our method on two datasets, MTOP and MultiATIS++SQL, establishing state-of-the-art results under a few-shot cross-lingual regime. Ablation studies further reveal that our method improves performance even without parallel input translations. In addition, we show that our model better captures cross-lingual structure in the latent space to improve semantic representation similarity.1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sherborne-etal-2023-optimal">
<titleInfo>
<title>Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Sherborne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hosking</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. Previous work has primarily considered silver-standard data augmentation or zero-shot methods; exploiting few-shot gold data is comparatively unexplored. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between probabilistic latent variables using Optimal Transport. We demonstrate how this direct guidance improves parsing from natural languages using fewer examples and less training. We evaluate our method on two datasets, MTOP and MultiATIS++SQL, establishing state-of-the-art results under a few-shot cross-lingual regime. Ablation studies further reveal that our method improves performance even without parallel input translations. In addition, we show that our model better captures cross-lingual structure in the latent space to improve semantic representation similarity.1</abstract>
<identifier type="citekey">sherborne-etal-2023-optimal</identifier>
<identifier type="doi">10.1162/tacl_a_00611</identifier>
<location>
<url>https://aclanthology.org/2023.tacl-1.81</url>
</location>
<part>
<date>2023</date>
<detail type="volume"><number>11</number></detail>
<extent unit="page">
<start>1432</start>
<end>1450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing
%A Sherborne, Tom
%A Hosking, Tom
%A Lapata, Mirella
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F sherborne-etal-2023-optimal
%X Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. Previous work has primarily considered silver-standard data augmentation or zero-shot methods; exploiting few-shot gold data is comparatively unexplored. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between probabilistic latent variables using Optimal Transport. We demonstrate how this direct guidance improves parsing from natural languages using fewer examples and less training. We evaluate our method on two datasets, MTOP and MultiATIS++SQL, establishing state-of-the-art results under a few-shot cross-lingual regime. Ablation studies further reveal that our method improves performance even without parallel input translations. In addition, we show that our model better captures cross-lingual structure in the latent space to improve semantic representation similarity.1
%R 10.1162/tacl_a_00611
%U https://aclanthology.org/2023.tacl-1.81
%U https://doi.org/10.1162/tacl_a_00611
%P 1432-1450
Markdown (Informal)
[Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing](https://aclanthology.org/2023.tacl-1.81) (Sherborne et al., TACL 2023)
ACL