@inproceedings{an-etal-2023-blm,
title = "{BLM}-{A}gr{F}: A New {F}rench Benchmark to Investigate Generalization of Agreement in Neural Networks",
author = "An, Aixiu and
Jiang, Chunyang and
A. Rodriguez, Maria and
Nastase, Vivi and
Merlo, Paola",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.99",
doi = "10.18653/v1/2023.eacl-main.99",
pages = "1363--1374",
abstract = "Successful machine learning systems currently rely on massive amounts of data, which are very effective in hiding some of the shallowness of the learned models. To help train models with more complex and compositional skills, we need challenging data, on which a system is successful only if it detects structure and regularities, that will allow it to generalize. In this paper, we describe a French dataset (BLM-AgrF) for learning the underlying rules of subject-verb agreement in sentences, developed in the BLM framework, a new task inspired by visual IQ tests known as Raven{'}s Progressive Matrices. In this task, an instance consists of sequences of sentences with specific attributes. To predict the correct answer as the next element of the sequence, a model must correctly detect the generative model used to produce the dataset. We provide details and share a dataset built following this methodology. Two exploratory baselines based on commonly used architectures show that despite the simplicity of the phenomenon, it is a complex problem for deep learning systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2023-blm">
<titleInfo>
<title>BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aixiu</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">A. Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivi</namePart>
<namePart type="family">Nastase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Successful machine learning systems currently rely on massive amounts of data, which are very effective in hiding some of the shallowness of the learned models. To help train models with more complex and compositional skills, we need challenging data, on which a system is successful only if it detects structure and regularities, that will allow it to generalize. In this paper, we describe a French dataset (BLM-AgrF) for learning the underlying rules of subject-verb agreement in sentences, developed in the BLM framework, a new task inspired by visual IQ tests known as Raven’s Progressive Matrices. In this task, an instance consists of sequences of sentences with specific attributes. To predict the correct answer as the next element of the sequence, a model must correctly detect the generative model used to produce the dataset. We provide details and share a dataset built following this methodology. Two exploratory baselines based on commonly used architectures show that despite the simplicity of the phenomenon, it is a complex problem for deep learning systems.</abstract>
<identifier type="citekey">an-etal-2023-blm</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.99</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.99</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1363</start>
<end>1374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks
%A An, Aixiu
%A Jiang, Chunyang
%A A. Rodriguez, Maria
%A Nastase, Vivi
%A Merlo, Paola
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F an-etal-2023-blm
%X Successful machine learning systems currently rely on massive amounts of data, which are very effective in hiding some of the shallowness of the learned models. To help train models with more complex and compositional skills, we need challenging data, on which a system is successful only if it detects structure and regularities, that will allow it to generalize. In this paper, we describe a French dataset (BLM-AgrF) for learning the underlying rules of subject-verb agreement in sentences, developed in the BLM framework, a new task inspired by visual IQ tests known as Raven’s Progressive Matrices. In this task, an instance consists of sequences of sentences with specific attributes. To predict the correct answer as the next element of the sequence, a model must correctly detect the generative model used to produce the dataset. We provide details and share a dataset built following this methodology. Two exploratory baselines based on commonly used architectures show that despite the simplicity of the phenomenon, it is a complex problem for deep learning systems.
%R 10.18653/v1/2023.eacl-main.99
%U https://aclanthology.org/2023.eacl-main.99
%U https://doi.org/10.18653/v1/2023.eacl-main.99
%P 1363-1374
Markdown (Informal)
[BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks](https://aclanthology.org/2023.eacl-main.99) (An et al., EACL 2023)
ACL