@inproceedings{croce-etal-2017-deep,
title = "Deep Learning in Semantic Kernel Spaces",
author = "Croce, Danilo and
Filice, Simone and
Castellucci, Giuseppe and
Basili, Roberto",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1032",
doi = "10.18653/v1/P17-1032",
pages = "345--354",
abstract = "Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks. Expressive kernels, such as Tree Kernels, achieve excellent performance in NLP. On the other side, deep neural networks have been demonstrated effective in automatically learning feature representations during training. However, their input is tensor data, i.e., they can not manage rich structured information. In this paper, we show that expressive kernels and deep neural networks can be combined in a common framework in order to (i) explicitly model structured information and (ii) learn non-linear decision functions. We show that the input layer of a deep architecture can be pre-trained through the application of the Nystrom low-rank approximation of kernel spaces. The resulting {``}kernelized{''} neural network achieves state-of-the-art accuracy in three different tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="croce-etal-2017-deep">
<titleInfo>
<title>Deep Learning in Semantic Kernel Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Filice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Castellucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Basili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks. Expressive kernels, such as Tree Kernels, achieve excellent performance in NLP. On the other side, deep neural networks have been demonstrated effective in automatically learning feature representations during training. However, their input is tensor data, i.e., they can not manage rich structured information. In this paper, we show that expressive kernels and deep neural networks can be combined in a common framework in order to (i) explicitly model structured information and (ii) learn non-linear decision functions. We show that the input layer of a deep architecture can be pre-trained through the application of the Nystrom low-rank approximation of kernel spaces. The resulting “kernelized” neural network achieves state-of-the-art accuracy in three different tasks.</abstract>
<identifier type="citekey">croce-etal-2017-deep</identifier>
<identifier type="doi">10.18653/v1/P17-1032</identifier>
<location>
<url>https://aclanthology.org/P17-1032</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>345</start>
<end>354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Learning in Semantic Kernel Spaces
%A Croce, Danilo
%A Filice, Simone
%A Castellucci, Giuseppe
%A Basili, Roberto
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F croce-etal-2017-deep
%X Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks. Expressive kernels, such as Tree Kernels, achieve excellent performance in NLP. On the other side, deep neural networks have been demonstrated effective in automatically learning feature representations during training. However, their input is tensor data, i.e., they can not manage rich structured information. In this paper, we show that expressive kernels and deep neural networks can be combined in a common framework in order to (i) explicitly model structured information and (ii) learn non-linear decision functions. We show that the input layer of a deep architecture can be pre-trained through the application of the Nystrom low-rank approximation of kernel spaces. The resulting “kernelized” neural network achieves state-of-the-art accuracy in three different tasks.
%R 10.18653/v1/P17-1032
%U https://aclanthology.org/P17-1032
%U https://doi.org/10.18653/v1/P17-1032
%P 345-354
Markdown (Informal)
[Deep Learning in Semantic Kernel Spaces](https://aclanthology.org/P17-1032) (Croce et al., ACL 2017)
ACL
- Danilo Croce, Simone Filice, Giuseppe Castellucci, and Roberto Basili. 2017. Deep Learning in Semantic Kernel Spaces. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 345–354, Vancouver, Canada. Association for Computational Linguistics.