@inproceedings{rademaker-etal-2023-semantic,
title = "Semantic Parsing and Sense Tagging the {P}rinceton {W}ord{N}et Gloss Corpus",
author = "Rademaker, Alexandre and
Basu, Abhishek and
Veluri, Rajkiran",
editor = "Rigau, German and
Bond, Francis and
Rademaker, Alexandre",
booktitle = "Proceedings of the 12th Global Wordnet Conference",
month = jan,
year = "2023",
address = "University of the Basque Country, Donostia - San Sebastian, Basque Country",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2023.gwc-1.30",
pages = "243--253",
abstract = "In 2008, the Princeton team released the last version of the {``}Princeton Annotated Gloss Corpus{''}. In this corpus. The word forms from the definitions and examples (glosses) of Princeton WordNet are manually linked to the context-appropriate sense in WordNet. However, the annotation was not complete, and the dataset was never officially released as part of WordNet 3.0, remaining as one of the standoff files available for download. Eleven years later, in 2019, one of the authors of this paper restarted the project aiming to complete the sense annotation of the approximately 200 thousand word forms not yet annotated. Here, we provide additional motivations to complete this dataset and report the progress in the work and evaluations. Intending to provide an extra level of consistency in the sense annotation and a deep semantic representation of the definitions and examples promoting WordNet from a lexical resource to a lightweight ontology, we now employ the English Resource Grammar (ERG), a broad-coverage HPSG grammar of English to parse the sentences and project the sense annotations from the surface words to the ERG predicates. We also report some initial steps on upgrading the corpus to WordNet 3.1 to facilitate mapping the data to other lexical resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rademaker-etal-2023-semantic">
<titleInfo>
<title>Semantic Parsing and Sense Tagging the Princeton WordNet Gloss Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Basu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajkiran</namePart>
<namePart type="family">Veluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">University of the Basque Country, Donostia - San Sebastian, Basque Country</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In 2008, the Princeton team released the last version of the “Princeton Annotated Gloss Corpus”. In this corpus. The word forms from the definitions and examples (glosses) of Princeton WordNet are manually linked to the context-appropriate sense in WordNet. However, the annotation was not complete, and the dataset was never officially released as part of WordNet 3.0, remaining as one of the standoff files available for download. Eleven years later, in 2019, one of the authors of this paper restarted the project aiming to complete the sense annotation of the approximately 200 thousand word forms not yet annotated. Here, we provide additional motivations to complete this dataset and report the progress in the work and evaluations. Intending to provide an extra level of consistency in the sense annotation and a deep semantic representation of the definitions and examples promoting WordNet from a lexical resource to a lightweight ontology, we now employ the English Resource Grammar (ERG), a broad-coverage HPSG grammar of English to parse the sentences and project the sense annotations from the surface words to the ERG predicates. We also report some initial steps on upgrading the corpus to WordNet 3.1 to facilitate mapping the data to other lexical resources.</abstract>
<identifier type="citekey">rademaker-etal-2023-semantic</identifier>
<location>
<url>https://aclanthology.org/2023.gwc-1.30</url>
</location>
<part>
<date>2023-01</date>
<extent unit="page">
<start>243</start>
<end>253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Parsing and Sense Tagging the Princeton WordNet Gloss Corpus
%A Rademaker, Alexandre
%A Basu, Abhishek
%A Veluri, Rajkiran
%Y Rigau, German
%Y Bond, Francis
%Y Rademaker, Alexandre
%S Proceedings of the 12th Global Wordnet Conference
%D 2023
%8 January
%I Global Wordnet Association
%C University of the Basque Country, Donostia - San Sebastian, Basque Country
%F rademaker-etal-2023-semantic
%X In 2008, the Princeton team released the last version of the “Princeton Annotated Gloss Corpus”. In this corpus. The word forms from the definitions and examples (glosses) of Princeton WordNet are manually linked to the context-appropriate sense in WordNet. However, the annotation was not complete, and the dataset was never officially released as part of WordNet 3.0, remaining as one of the standoff files available for download. Eleven years later, in 2019, one of the authors of this paper restarted the project aiming to complete the sense annotation of the approximately 200 thousand word forms not yet annotated. Here, we provide additional motivations to complete this dataset and report the progress in the work and evaluations. Intending to provide an extra level of consistency in the sense annotation and a deep semantic representation of the definitions and examples promoting WordNet from a lexical resource to a lightweight ontology, we now employ the English Resource Grammar (ERG), a broad-coverage HPSG grammar of English to parse the sentences and project the sense annotations from the surface words to the ERG predicates. We also report some initial steps on upgrading the corpus to WordNet 3.1 to facilitate mapping the data to other lexical resources.
%U https://aclanthology.org/2023.gwc-1.30
%P 243-253
Markdown (Informal)
[Semantic Parsing and Sense Tagging the Princeton WordNet Gloss Corpus](https://aclanthology.org/2023.gwc-1.30) (Rademaker et al., GWC 2023)
ACL