@inproceedings{schouten-etal-2022-probing,
title = "Probing the representations of named entities in Transformer-based Language Models",
author = "Schouten, Stefan and
Bloem, Peter and
Vossen, Piek",
editor = "Bastings, Jasmijn and
Belinkov, Yonatan and
Elazar, Yanai and
Hupkes, Dieuwke and
Saphra, Naomi and
Wiegreffe, Sarah",
booktitle = "Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.blackboxnlp-1.32",
doi = "10.18653/v1/2022.blackboxnlp-1.32",
pages = "384--393",
abstract = "In this work we analyze the named entity representations learned by Transformer-based language models. We investigate the role entities play in two tasks: a language modeling task, and a sequence classification task. For this purpose we collect a novel news topic classification dataset with 12 topics called RefNews-12. We perform two complementary methods of analysis. First, we use diagnostic models allowing us to quantify to what degree entity information is present in the hidden representations. Second, we perform entity mention substitution to measure how substitute-entities with different properties impact model performance. By controlling for model uncertainty we are able to show that entities are identified, and depending on the task, play a measurable role in the model{'}s predictions. Additionally, we show that the entities{'} types alone are not enough to account for this. Finally, we find that the the frequency with which entities occur are important for the masked language modeling task, and that the entities{'} distributions over topics are important for topic classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schouten-etal-2022-probing">
<titleInfo>
<title>Probing the representations of named entities in Transformer-based Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Schouten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bloem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</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 Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasmijn</namePart>
<namePart type="family">Bastings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanai</namePart>
<namePart type="family">Elazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Wiegreffe</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>In this work we analyze the named entity representations learned by Transformer-based language models. We investigate the role entities play in two tasks: a language modeling task, and a sequence classification task. For this purpose we collect a novel news topic classification dataset with 12 topics called RefNews-12. We perform two complementary methods of analysis. First, we use diagnostic models allowing us to quantify to what degree entity information is present in the hidden representations. Second, we perform entity mention substitution to measure how substitute-entities with different properties impact model performance. By controlling for model uncertainty we are able to show that entities are identified, and depending on the task, play a measurable role in the model’s predictions. Additionally, we show that the entities’ types alone are not enough to account for this. Finally, we find that the the frequency with which entities occur are important for the masked language modeling task, and that the entities’ distributions over topics are important for topic classification.</abstract>
<identifier type="citekey">schouten-etal-2022-probing</identifier>
<identifier type="doi">10.18653/v1/2022.blackboxnlp-1.32</identifier>
<location>
<url>https://aclanthology.org/2022.blackboxnlp-1.32</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>384</start>
<end>393</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing the representations of named entities in Transformer-based Language Models
%A Schouten, Stefan
%A Bloem, Peter
%A Vossen, Piek
%Y Bastings, Jasmijn
%Y Belinkov, Yonatan
%Y Elazar, Yanai
%Y Hupkes, Dieuwke
%Y Saphra, Naomi
%Y Wiegreffe, Sarah
%S Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F schouten-etal-2022-probing
%X In this work we analyze the named entity representations learned by Transformer-based language models. We investigate the role entities play in two tasks: a language modeling task, and a sequence classification task. For this purpose we collect a novel news topic classification dataset with 12 topics called RefNews-12. We perform two complementary methods of analysis. First, we use diagnostic models allowing us to quantify to what degree entity information is present in the hidden representations. Second, we perform entity mention substitution to measure how substitute-entities with different properties impact model performance. By controlling for model uncertainty we are able to show that entities are identified, and depending on the task, play a measurable role in the model’s predictions. Additionally, we show that the entities’ types alone are not enough to account for this. Finally, we find that the the frequency with which entities occur are important for the masked language modeling task, and that the entities’ distributions over topics are important for topic classification.
%R 10.18653/v1/2022.blackboxnlp-1.32
%U https://aclanthology.org/2022.blackboxnlp-1.32
%U https://doi.org/10.18653/v1/2022.blackboxnlp-1.32
%P 384-393
Markdown (Informal)
[Probing the representations of named entities in Transformer-based Language Models](https://aclanthology.org/2022.blackboxnlp-1.32) (Schouten et al., BlackboxNLP 2022)
ACL