@inproceedings{kolluru-etal-2022-covid,
title = "{``}Covid vaccine is against Covid but {O}xford vaccine is made at {O}xford!{''} Semantic Interpretation of Proper Noun Compounds",
author = "Kolluru, Keshav and
Stanovsky, Gabriel and
{Mausam}",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.711",
doi = "10.18653/v1/2022.emnlp-main.711",
pages = "10407--10420",
abstract = "Proper noun compounds, e.g., {``}Covid vaccine{''}, convey information in a succinct manner (a {``}Covid vaccine{''} is a {``}vaccine that immunizes against the Covid disease{''}). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8{\%}. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5{\%} increase in yield at a precision of 85{\%}. The dataset and code are available at \url{https://github.com/dair-iitd/pronci}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolluru-etal-2022-covid">
<titleInfo>
<title>“Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun Compounds</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keshav</namePart>
<namePart type="family">Kolluru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Proper noun compounds, e.g., “Covid vaccine”, convey information in a succinct manner (a “Covid vaccine” is a “vaccine that immunizes against the Covid disease”). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8%. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5% increase in yield at a precision of 85%. The dataset and code are available at https://github.com/dair-iitd/pronci.</abstract>
<identifier type="citekey">kolluru-etal-2022-covid</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.711</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.711</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10407</start>
<end>10420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun Compounds
%A Kolluru, Keshav
%A Stanovsky, Gabriel
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%A Mausam
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kolluru-etal-2022-covid
%X Proper noun compounds, e.g., “Covid vaccine”, convey information in a succinct manner (a “Covid vaccine” is a “vaccine that immunizes against the Covid disease”). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8%. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5% increase in yield at a precision of 85%. The dataset and code are available at https://github.com/dair-iitd/pronci.
%R 10.18653/v1/2022.emnlp-main.711
%U https://aclanthology.org/2022.emnlp-main.711
%U https://doi.org/10.18653/v1/2022.emnlp-main.711
%P 10407-10420
Markdown (Informal)
[“Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun Compounds](https://aclanthology.org/2022.emnlp-main.711) (Kolluru et al., EMNLP 2022)
ACL