@inproceedings{qin-etal-2018-learning,
title = "Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data",
author = "Qin, Guanghui and
Yao, Jin-Ge and
Wang, Xuening and
Wang, Jinpeng and
Lin, Chin-Yew",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1411",
doi = "10.18653/v1/D18-1411",
pages = "3761--3771",
abstract = "Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms. In this paper, we attempt at learning explicit latent semantic annotations from paired structured tables and texts, establishing correspondences between various types of values and texts. We model the joint probability of data fields, texts, phrasal spans, and latent annotations with an adapted semi-hidden Markov model, and impose a soft statistical constraint to further improve the performance. As a by-product, we leverage the induced annotations to extract templates for language generation. Experimental results suggest the feasibility of the setting in this study, as well as the effectiveness of our proposed framework.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2018-learning">
<titleInfo>
<title>Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanghui</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Ge</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuening</namePart>
<namePart type="family">Wang</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>2018-oct"-"nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms. In this paper, we attempt at learning explicit latent semantic annotations from paired structured tables and texts, establishing correspondences between various types of values and texts. We model the joint probability of data fields, texts, phrasal spans, and latent annotations with an adapted semi-hidden Markov model, and impose a soft statistical constraint to further improve the performance. As a by-product, we leverage the induced annotations to extract templates for language generation. Experimental results suggest the feasibility of the setting in this study, as well as the effectiveness of our proposed framework.</abstract>
<identifier type="citekey">qin-etal-2018-learning</identifier>
<identifier type="doi">10.18653/v1/D18-1411</identifier>
<location>
<url>https://aclanthology.org/D18-1411</url>
</location>
<part>
<date>2018-oct"-"nov</date>
<extent unit="page">
<start>3761</start>
<end>3771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data
%A Qin, Guanghui
%A Yao, Jin-Ge
%A Wang, Xuening
%A Wang, Jinpeng
%A Lin, Chin-Yew
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F qin-etal-2018-learning
%X Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms. In this paper, we attempt at learning explicit latent semantic annotations from paired structured tables and texts, establishing correspondences between various types of values and texts. We model the joint probability of data fields, texts, phrasal spans, and latent annotations with an adapted semi-hidden Markov model, and impose a soft statistical constraint to further improve the performance. As a by-product, we leverage the induced annotations to extract templates for language generation. Experimental results suggest the feasibility of the setting in this study, as well as the effectiveness of our proposed framework.
%R 10.18653/v1/D18-1411
%U https://aclanthology.org/D18-1411
%U https://doi.org/10.18653/v1/D18-1411
%P 3761-3771
Markdown (Informal)
[Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data](https://aclanthology.org/D18-1411) (Qin et al., EMNLP 2018)
ACL