@inproceedings{luo-zhu-2022-recurrent,
title = "Recurrent Neural Networks with Mixed Hierarchical Structures and {EM} Algorithm for Natural Language Processing",
author = "Luo, Zhaoxin and
Zhu, Michael",
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-1.656",
pages = "6104--6113",
abstract = "How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and implicit hierarchical information in modeling languages in the literature. In this paper, we propose a novel approach called the latent indicator layer to identify and learn implicit hierarchical information (e.g., phrases), and further develop an EM algorithm to handle the latent indicator layer in training. The latent indicator layer further simplifies a text{'}s hierarchical structure, which allows us to seamlessly integrate different levels of attention mechanisms into the structure. We called the resulting architecture as the EM-HRNN model. Furthermore, we develop two bootstrap strategies to effectively and efficiently train the EM-HRNN model on long text documents. Simulation studies and real data applications demonstrate that the EM-HRNN model with bootstrap training outperforms other RNN-based models in document classification tasks. The performance of the EM-HRNN model is comparable to a Transformer-based method called Bert-base, though the former is much smaller model and does not require pre-training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-zhu-2022-recurrent">
<titleInfo>
<title>Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaoxin</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Zhu</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>How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and implicit hierarchical information in modeling languages in the literature. In this paper, we propose a novel approach called the latent indicator layer to identify and learn implicit hierarchical information (e.g., phrases), and further develop an EM algorithm to handle the latent indicator layer in training. The latent indicator layer further simplifies a text’s hierarchical structure, which allows us to seamlessly integrate different levels of attention mechanisms into the structure. We called the resulting architecture as the EM-HRNN model. Furthermore, we develop two bootstrap strategies to effectively and efficiently train the EM-HRNN model on long text documents. Simulation studies and real data applications demonstrate that the EM-HRNN model with bootstrap training outperforms other RNN-based models in document classification tasks. The performance of the EM-HRNN model is comparable to a Transformer-based method called Bert-base, though the former is much smaller model and does not require pre-training.</abstract>
<identifier type="citekey">luo-zhu-2022-recurrent</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.656</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6104</start>
<end>6113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing
%A Luo, Zhaoxin
%A Zhu, Michael
%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 luo-zhu-2022-recurrent
%X How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and implicit hierarchical information in modeling languages in the literature. In this paper, we propose a novel approach called the latent indicator layer to identify and learn implicit hierarchical information (e.g., phrases), and further develop an EM algorithm to handle the latent indicator layer in training. The latent indicator layer further simplifies a text’s hierarchical structure, which allows us to seamlessly integrate different levels of attention mechanisms into the structure. We called the resulting architecture as the EM-HRNN model. Furthermore, we develop two bootstrap strategies to effectively and efficiently train the EM-HRNN model on long text documents. Simulation studies and real data applications demonstrate that the EM-HRNN model with bootstrap training outperforms other RNN-based models in document classification tasks. The performance of the EM-HRNN model is comparable to a Transformer-based method called Bert-base, though the former is much smaller model and does not require pre-training.
%U https://aclanthology.org/2022.lrec-1.656
%P 6104-6113
Markdown (Informal)
[Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing](https://aclanthology.org/2022.lrec-1.656) (Luo & Zhu, LREC 2022)
ACL