@inproceedings{rahimi-surdeanu-2022-transformer,
title = "Do Transformer Networks Improve the Discovery of Rules from Text?",
author = "Rahimi, Mahdi and
Surdeanu, Mihai",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.395",
pages = "3706--3714",
abstract = "With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to rules that model binary relations such as X treat Y. DIRT{'}s relevance is renewed in today{'}s neural era given the recent focus on interpretability in the field of natural language processing. We propose a novel take on the DIRT algorithm, where we implement the distributional hypothesis using the contextualized embeddings provided by BERT, a transformer-network-based language model (Vaswani et al. 2017; Devlin et al. 2018). In particular, we change the similarity measure between pairs of slots (i.e., the set of words matched by a rule) from the original formula that relies on lexical items to a formula computed using contextualized embeddings. We empirically demonstrate that this new similarity method yields a better implementation of the distributional hypothesis, and this, in turn, yields rules that outperform the original algorithm in the question answering-based evaluation proposed by Lin and Pantel (2001).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahimi-surdeanu-2022-transformer">
<titleInfo>
<title>Do Transformer Networks Improve the Discovery of Rules from Text?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahdi</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to rules that model binary relations such as X treat Y. DIRT’s relevance is renewed in today’s neural era given the recent focus on interpretability in the field of natural language processing. We propose a novel take on the DIRT algorithm, where we implement the distributional hypothesis using the contextualized embeddings provided by BERT, a transformer-network-based language model (Vaswani et al. 2017; Devlin et al. 2018). In particular, we change the similarity measure between pairs of slots (i.e., the set of words matched by a rule) from the original formula that relies on lexical items to a formula computed using contextualized embeddings. We empirically demonstrate that this new similarity method yields a better implementation of the distributional hypothesis, and this, in turn, yields rules that outperform the original algorithm in the question answering-based evaluation proposed by Lin and Pantel (2001).</abstract>
<identifier type="citekey">rahimi-surdeanu-2022-transformer</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.395</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3706</start>
<end>3714</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Transformer Networks Improve the Discovery of Rules from Text?
%A Rahimi, Mahdi
%A Surdeanu, Mihai
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F rahimi-surdeanu-2022-transformer
%X With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to rules that model binary relations such as X treat Y. DIRT’s relevance is renewed in today’s neural era given the recent focus on interpretability in the field of natural language processing. We propose a novel take on the DIRT algorithm, where we implement the distributional hypothesis using the contextualized embeddings provided by BERT, a transformer-network-based language model (Vaswani et al. 2017; Devlin et al. 2018). In particular, we change the similarity measure between pairs of slots (i.e., the set of words matched by a rule) from the original formula that relies on lexical items to a formula computed using contextualized embeddings. We empirically demonstrate that this new similarity method yields a better implementation of the distributional hypothesis, and this, in turn, yields rules that outperform the original algorithm in the question answering-based evaluation proposed by Lin and Pantel (2001).
%U https://aclanthology.org/2022.lrec-1.395
%P 3706-3714
Markdown (Informal)
[Do Transformer Networks Improve the Discovery of Rules from Text?](https://aclanthology.org/2022.lrec-1.395) (Rahimi & Surdeanu, LREC 2022)
ACL