@inproceedings{voigt-etal-2022-keywordscape,
title = "{K}eyword{S}cape: Visual Document Exploration using Contextualized Keyword Embeddings",
author = "Voigt, Henrik and
Meuschke, Monique and
Zarrie{\ss}, Sina and
Lawonn, Kai",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.14",
doi = "10.18653/v1/2022.emnlp-demos.14",
pages = "137--147",
abstract = "Although contextualized word embeddings have led to great improvements in automatic language understanding, their potential for practical applications in document exploration and visualization has been little explored. Common visualization techniques used for, e.g., model analysis usually provide simple scatter plots of token-level embeddings that do not provide insight into their contextual use. In this work, we propose KeywordScape, a visual exploration tool that allows to overview, summarize, and explore the semantic content of documents based on their keywords. While existing keyword-based exploration tools assume that keywords have static meanings, our tool represents keywords in terms of their contextualized embeddings. Our application visualizes these embeddings in a semantic landscape that represents keywords as islands on a spherical map. This keeps keywords with similar context close to each other, allowing for a more precise search and comparison of documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="voigt-etal-2022-keywordscape">
<titleInfo>
<title>KeywordScape: Visual Document Exploration using Contextualized Keyword Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henrik</namePart>
<namePart type="family">Voigt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monique</namePart>
<namePart type="family">Meuschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Lawonn</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although contextualized word embeddings have led to great improvements in automatic language understanding, their potential for practical applications in document exploration and visualization has been little explored. Common visualization techniques used for, e.g., model analysis usually provide simple scatter plots of token-level embeddings that do not provide insight into their contextual use. In this work, we propose KeywordScape, a visual exploration tool that allows to overview, summarize, and explore the semantic content of documents based on their keywords. While existing keyword-based exploration tools assume that keywords have static meanings, our tool represents keywords in terms of their contextualized embeddings. Our application visualizes these embeddings in a semantic landscape that represents keywords as islands on a spherical map. This keeps keywords with similar context close to each other, allowing for a more precise search and comparison of documents.</abstract>
<identifier type="citekey">voigt-etal-2022-keywordscape</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.14</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.14</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>137</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KeywordScape: Visual Document Exploration using Contextualized Keyword Embeddings
%A Voigt, Henrik
%A Meuschke, Monique
%A Zarrieß, Sina
%A Lawonn, Kai
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F voigt-etal-2022-keywordscape
%X Although contextualized word embeddings have led to great improvements in automatic language understanding, their potential for practical applications in document exploration and visualization has been little explored. Common visualization techniques used for, e.g., model analysis usually provide simple scatter plots of token-level embeddings that do not provide insight into their contextual use. In this work, we propose KeywordScape, a visual exploration tool that allows to overview, summarize, and explore the semantic content of documents based on their keywords. While existing keyword-based exploration tools assume that keywords have static meanings, our tool represents keywords in terms of their contextualized embeddings. Our application visualizes these embeddings in a semantic landscape that represents keywords as islands on a spherical map. This keeps keywords with similar context close to each other, allowing for a more precise search and comparison of documents.
%R 10.18653/v1/2022.emnlp-demos.14
%U https://aclanthology.org/2022.emnlp-demos.14
%U https://doi.org/10.18653/v1/2022.emnlp-demos.14
%P 137-147
Markdown (Informal)
[KeywordScape: Visual Document Exploration using Contextualized Keyword Embeddings](https://aclanthology.org/2022.emnlp-demos.14) (Voigt et al., EMNLP 2022)
ACL