@inproceedings{newman-griffis-etal-2021-textessence,
title = "{T}ext{E}ssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora",
author = "Newman-Griffis, Denis and
Sivaraman, Venkatesh and
Perer, Adam and
Fosler-Lussier, Eric and
Hochheiser, Harry",
editor = "Sil, Avi and
Lin, Xi Victoria",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-demos.13",
doi = "10.18653/v1/2021.naacl-demos.13",
pages = "106--115",
abstract = "Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality embeddings for corpus analysis. A case study on COVID-19 scientific literature illustrates the utility of the system. TextEssence can be found at \url{https://textessence.github.io}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="newman-griffis-etal-2021-textessence">
<titleInfo>
<title>TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Newman-Griffis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Venkatesh</namePart>
<namePart type="family">Sivaraman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Perer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Fosler-Lussier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harry</namePart>
<namePart type="family">Hochheiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality embeddings for corpus analysis. A case study on COVID-19 scientific literature illustrates the utility of the system. TextEssence can be found at https://textessence.github.io.</abstract>
<identifier type="citekey">newman-griffis-etal-2021-textessence</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-demos.13</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-demos.13</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>106</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora
%A Newman-Griffis, Denis
%A Sivaraman, Venkatesh
%A Perer, Adam
%A Fosler-Lussier, Eric
%A Hochheiser, Harry
%Y Sil, Avi
%Y Lin, Xi Victoria
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F newman-griffis-etal-2021-textessence
%X Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality embeddings for corpus analysis. A case study on COVID-19 scientific literature illustrates the utility of the system. TextEssence can be found at https://textessence.github.io.
%R 10.18653/v1/2021.naacl-demos.13
%U https://aclanthology.org/2021.naacl-demos.13
%U https://doi.org/10.18653/v1/2021.naacl-demos.13
%P 106-115
Markdown (Informal)
[TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora](https://aclanthology.org/2021.naacl-demos.13) (Newman-Griffis et al., NAACL 2021)
ACL
- Denis Newman-Griffis, Venkatesh Sivaraman, Adam Perer, Eric Fosler-Lussier, and Harry Hochheiser. 2021. TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations, pages 106–115, Online. Association for Computational Linguistics.