@inproceedings{van-boven-bloem-2022-domain,
title = "Domain-specific Evaluation of Word Embeddings for Philosophical Text using Direct Intrinsic Evaluation",
author = "van Boven, Goya and
Bloem, Jelke",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Alnajjar, Khalid and
Partanen, Niko and
Rueter, Jack},
booktitle = "Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities",
month = nov,
year = "2022",
address = "Taipei, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlp4dh-1.14",
pages = "101--107",
abstract = "We perform a direct intrinsic evaluation of word embeddings trained on the works of a single philosopher. Six models are compared to human judgements elicited using two tasks: a synonym detection task and a coherence task. We apply a method that elicits judgements based on explicit knowledge from experts, as the linguistic intuition of non-expert participants might differ from that of the philosopher. We find that an in-domain SVD model has the best 1-nearest neighbours for target terms, while transfer learning-based Nonce2Vec performs better for low frequency target terms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-boven-bloem-2022-domain">
<titleInfo>
<title>Domain-specific Evaluation of Word Embeddings for Philosophical Text using Direct Intrinsic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goya</namePart>
<namePart type="family">van Boven</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We perform a direct intrinsic evaluation of word embeddings trained on the works of a single philosopher. Six models are compared to human judgements elicited using two tasks: a synonym detection task and a coherence task. We apply a method that elicits judgements based on explicit knowledge from experts, as the linguistic intuition of non-expert participants might differ from that of the philosopher. We find that an in-domain SVD model has the best 1-nearest neighbours for target terms, while transfer learning-based Nonce2Vec performs better for low frequency target terms.</abstract>
<identifier type="citekey">van-boven-bloem-2022-domain</identifier>
<location>
<url>https://aclanthology.org/2022.nlp4dh-1.14</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>101</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-specific Evaluation of Word Embeddings for Philosophical Text using Direct Intrinsic Evaluation
%A van Boven, Goya
%A Bloem, Jelke
%Y Hämäläinen, Mika
%Y Alnajjar, Khalid
%Y Partanen, Niko
%Y Rueter, Jack
%S Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities
%D 2022
%8 November
%I Association for Computational Linguistics
%C Taipei, Taiwan
%F van-boven-bloem-2022-domain
%X We perform a direct intrinsic evaluation of word embeddings trained on the works of a single philosopher. Six models are compared to human judgements elicited using two tasks: a synonym detection task and a coherence task. We apply a method that elicits judgements based on explicit knowledge from experts, as the linguistic intuition of non-expert participants might differ from that of the philosopher. We find that an in-domain SVD model has the best 1-nearest neighbours for target terms, while transfer learning-based Nonce2Vec performs better for low frequency target terms.
%U https://aclanthology.org/2022.nlp4dh-1.14
%P 101-107
Markdown (Informal)
[Domain-specific Evaluation of Word Embeddings for Philosophical Text using Direct Intrinsic Evaluation](https://aclanthology.org/2022.nlp4dh-1.14) (van Boven & Bloem, NLP4DH 2022)
ACL