@inproceedings{nie-etal-2020-learning,
title = "Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments",
author = "Nie, Feng and
Wang, Jinpeng and
Lin, Chin-Yew",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.272",
doi = "10.18653/v1/2020.coling-main.272",
pages = "3050--3059",
abstract = "Learning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation. Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input. To learn semantic correspondences from such datasets, we propose a two-stage local-to-global alignment (L2GA) framework. First, a local model based on multi-instance learning is applied to build alignments for texts spans that can be directly grounded to its paired structured input. Then, a novel global model built upon a memory-guided conditional random field (CRF) layer aims to infer missing alignments for text spans which not supported by paired incomplete inputs, where the memory is designed to leverage alignment clues provided by the local model to strengthen the global model. In this way, the local model and global model can work jointly to learn semantic correspondences in the same framework. Experimental results show that our proposed method can be generalized to both restaurant and computer domains and improve the alignment accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nie-etal-2020-learning">
<titleInfo>
<title>Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chin-Yew</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation. Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input. To learn semantic correspondences from such datasets, we propose a two-stage local-to-global alignment (L2GA) framework. First, a local model based on multi-instance learning is applied to build alignments for texts spans that can be directly grounded to its paired structured input. Then, a novel global model built upon a memory-guided conditional random field (CRF) layer aims to infer missing alignments for text spans which not supported by paired incomplete inputs, where the memory is designed to leverage alignment clues provided by the local model to strengthen the global model. In this way, the local model and global model can work jointly to learn semantic correspondences in the same framework. Experimental results show that our proposed method can be generalized to both restaurant and computer domains and improve the alignment accuracy.</abstract>
<identifier type="citekey">nie-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.272</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.272</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3050</start>
<end>3059</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments
%A Nie, Feng
%A Wang, Jinpeng
%A Lin, Chin-Yew
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F nie-etal-2020-learning
%X Learning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation. Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input. To learn semantic correspondences from such datasets, we propose a two-stage local-to-global alignment (L2GA) framework. First, a local model based on multi-instance learning is applied to build alignments for texts spans that can be directly grounded to its paired structured input. Then, a novel global model built upon a memory-guided conditional random field (CRF) layer aims to infer missing alignments for text spans which not supported by paired incomplete inputs, where the memory is designed to leverage alignment clues provided by the local model to strengthen the global model. In this way, the local model and global model can work jointly to learn semantic correspondences in the same framework. Experimental results show that our proposed method can be generalized to both restaurant and computer domains and improve the alignment accuracy.
%R 10.18653/v1/2020.coling-main.272
%U https://aclanthology.org/2020.coling-main.272
%U https://doi.org/10.18653/v1/2020.coling-main.272
%P 3050-3059
Markdown (Informal)
[Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments](https://aclanthology.org/2020.coling-main.272) (Nie et al., COLING 2020)
ACL