@inproceedings{reusch-lehner-2022-extracting,
title = "Extracting Operator Trees from Model Embeddings",
author = "Reusch, Anja and
Lehner, Wolfgang",
editor = "Ferreira, Deborah and
Valentino, Marco and
Freitas, Andre and
Welleck, Sean and
Schubotz, Moritz",
booktitle = "Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mathnlp-1.6",
doi = "10.18653/v1/2022.mathnlp-1.6",
pages = "40--50",
abstract = "Transformer-based language models are able to capture several linguistic properties such as hierarchical structures like dependency or constituency trees. Whether similar structures for mathematics are extractable from language models has not yet been explored. This work aims to probe current state-of-the-art models for the extractability of Operator Trees from their contextualized embeddings using the structure probe designed by Hewitt and Manning. We release the code and our data set for future analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reusch-lehner-2022-extracting">
<titleInfo>
<title>Extracting Operator Trees from Model Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anja</namePart>
<namePart type="family">Reusch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Lehner</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 1st Workshop on Mathematical Natural Language Processing (MathNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deborah</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Welleck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Schubotz</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>Transformer-based language models are able to capture several linguistic properties such as hierarchical structures like dependency or constituency trees. Whether similar structures for mathematics are extractable from language models has not yet been explored. This work aims to probe current state-of-the-art models for the extractability of Operator Trees from their contextualized embeddings using the structure probe designed by Hewitt and Manning. We release the code and our data set for future analysis.</abstract>
<identifier type="citekey">reusch-lehner-2022-extracting</identifier>
<identifier type="doi">10.18653/v1/2022.mathnlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.mathnlp-1.6</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>40</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting Operator Trees from Model Embeddings
%A Reusch, Anja
%A Lehner, Wolfgang
%Y Ferreira, Deborah
%Y Valentino, Marco
%Y Freitas, Andre
%Y Welleck, Sean
%Y Schubotz, Moritz
%S Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F reusch-lehner-2022-extracting
%X Transformer-based language models are able to capture several linguistic properties such as hierarchical structures like dependency or constituency trees. Whether similar structures for mathematics are extractable from language models has not yet been explored. This work aims to probe current state-of-the-art models for the extractability of Operator Trees from their contextualized embeddings using the structure probe designed by Hewitt and Manning. We release the code and our data set for future analysis.
%R 10.18653/v1/2022.mathnlp-1.6
%U https://aclanthology.org/2022.mathnlp-1.6
%U https://doi.org/10.18653/v1/2022.mathnlp-1.6
%P 40-50
Markdown (Informal)
[Extracting Operator Trees from Model Embeddings](https://aclanthology.org/2022.mathnlp-1.6) (Reusch & Lehner, MathNLP 2022)
ACL
- Anja Reusch and Wolfgang Lehner. 2022. Extracting Operator Trees from Model Embeddings. In Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP), pages 40–50, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.