@inproceedings{aracena-etal-2022-knowledge,
title = "A Knowledge-Graph-Based Intrinsic Test for Benchmarking Medical Concept Embeddings and Pretrained Language Models",
author = "Aracena, Claudio and
Villena, Fabi{\'a}n and
Rojas, Matias and
Dunstan, Jocelyn",
editor = "Lavelli, Alberto and
Holderness, Eben and
Jimeno Yepes, Antonio and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.louhi-1.22",
doi = "10.18653/v1/2022.louhi-1.22",
pages = "197--206",
abstract = "Using language models created from large data sources has improved the performance of several deep learning-based architectures, obtaining state-of-the-art results in several NLP extrinsic tasks. However, little research is related to creating intrinsic tests that allow us to compare the quality of different language models when obtaining contextualized embeddings. This gap increases even more when working on specific domains in languages other than English. This paper proposes a novel graph-based intrinsic test that allows us to measure the quality of different language models in clinical and biomedical domains in Spanish. Our results show that our intrinsic test performs better for clinical and biomedical language models than a general one. Also, it correlates with better outcomes for a NER task using a probing model over contextualized embeddings. We hope our work will help the clinical NLP research community to evaluate and compare new language models in other languages and find the most suitable models for solving downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aracena-etal-2022-knowledge">
<titleInfo>
<title>A Knowledge-Graph-Based Intrinsic Test for Benchmarking Medical Concept Embeddings and Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Aracena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabián</namePart>
<namePart type="family">Villena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matias</namePart>
<namePart type="family">Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jocelyn</namePart>
<namePart type="family">Dunstan</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 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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 (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Using language models created from large data sources has improved the performance of several deep learning-based architectures, obtaining state-of-the-art results in several NLP extrinsic tasks. However, little research is related to creating intrinsic tests that allow us to compare the quality of different language models when obtaining contextualized embeddings. This gap increases even more when working on specific domains in languages other than English. This paper proposes a novel graph-based intrinsic test that allows us to measure the quality of different language models in clinical and biomedical domains in Spanish. Our results show that our intrinsic test performs better for clinical and biomedical language models than a general one. Also, it correlates with better outcomes for a NER task using a probing model over contextualized embeddings. We hope our work will help the clinical NLP research community to evaluate and compare new language models in other languages and find the most suitable models for solving downstream tasks.</abstract>
<identifier type="citekey">aracena-etal-2022-knowledge</identifier>
<identifier type="doi">10.18653/v1/2022.louhi-1.22</identifier>
<location>
<url>https://aclanthology.org/2022.louhi-1.22</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>197</start>
<end>206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Knowledge-Graph-Based Intrinsic Test for Benchmarking Medical Concept Embeddings and Pretrained Language Models
%A Aracena, Claudio
%A Villena, Fabián
%A Rojas, Matias
%A Dunstan, Jocelyn
%Y Lavelli, Alberto
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F aracena-etal-2022-knowledge
%X Using language models created from large data sources has improved the performance of several deep learning-based architectures, obtaining state-of-the-art results in several NLP extrinsic tasks. However, little research is related to creating intrinsic tests that allow us to compare the quality of different language models when obtaining contextualized embeddings. This gap increases even more when working on specific domains in languages other than English. This paper proposes a novel graph-based intrinsic test that allows us to measure the quality of different language models in clinical and biomedical domains in Spanish. Our results show that our intrinsic test performs better for clinical and biomedical language models than a general one. Also, it correlates with better outcomes for a NER task using a probing model over contextualized embeddings. We hope our work will help the clinical NLP research community to evaluate and compare new language models in other languages and find the most suitable models for solving downstream tasks.
%R 10.18653/v1/2022.louhi-1.22
%U https://aclanthology.org/2022.louhi-1.22
%U https://doi.org/10.18653/v1/2022.louhi-1.22
%P 197-206
Markdown (Informal)
[A Knowledge-Graph-Based Intrinsic Test for Benchmarking Medical Concept Embeddings and Pretrained Language Models](https://aclanthology.org/2022.louhi-1.22) (Aracena et al., Louhi 2022)
ACL