@inproceedings{godin-etal-2017-improving,
title = "Improving Language Modeling using Densely Connected Recurrent Neural Networks",
author = "Godin, Fr{\'e}deric and
Dambre, Joni and
De Neve, Wesley",
editor = "Blunsom, Phil and
Bordes, Antoine and
Cho, Kyunghyun and
Cohen, Shay and
Dyer, Chris and
Grefenstette, Edward and
Hermann, Karl Moritz and
Rimell, Laura and
Weston, Jason and
Yih, Scott",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2622/",
doi = "10.18653/v1/W17-2622",
pages = "186--190",
abstract = "In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al., 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="godin-etal-2017-improving">
<titleInfo>
<title>Improving Language Modeling using Densely Connected Recurrent Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fréderic</namePart>
<namePart type="family">Godin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joni</namePart>
<namePart type="family">Dambre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wesley</namePart>
<namePart type="family">De Neve</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="given">Moritz</namePart>
<namePart type="family">Hermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Weston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Yih</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>In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al., 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.</abstract>
<identifier type="citekey">godin-etal-2017-improving</identifier>
<identifier type="doi">10.18653/v1/W17-2622</identifier>
<location>
<url>https://aclanthology.org/W17-2622/</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>186</start>
<end>190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Language Modeling using Densely Connected Recurrent Neural Networks
%A Godin, Fréderic
%A Dambre, Joni
%A De Neve, Wesley
%Y Blunsom, Phil
%Y Bordes, Antoine
%Y Cho, Kyunghyun
%Y Cohen, Shay
%Y Dyer, Chris
%Y Grefenstette, Edward
%Y Hermann, Karl Moritz
%Y Rimell, Laura
%Y Weston, Jason
%Y Yih, Scott
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F godin-etal-2017-improving
%X In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al., 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.
%R 10.18653/v1/W17-2622
%U https://aclanthology.org/W17-2622/
%U https://doi.org/10.18653/v1/W17-2622
%P 186-190
Markdown (Informal)
[Improving Language Modeling using Densely Connected Recurrent Neural Networks](https://aclanthology.org/W17-2622/) (Godin et al., RepL4NLP 2017)
ACL