@inproceedings{takase-etal-2018-direct,
title = "Direct Output Connection for a High-Rank Language Model",
author = "Takase, Sho and
Suzuki, Jun and
Nagata, Masaaki",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1489",
doi = "10.18653/v1/D18-1489",
pages = "4599--4609",
abstract = "This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also middle layers. This method raises the expressive power of a language model based on the matrix factorization interpretation of language modeling introduced by Yang et al. (2018). Our proposed method improves the current state-of-the-art language model and achieves the best score on the Penn Treebank and WikiText-2, which are the standard benchmark datasets. Moreover, we indicate our proposed method contributes to application tasks: machine translation and headline generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takase-etal-2018-direct">
<titleInfo>
<title>Direct Output Connection for a High-Rank Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Takase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also middle layers. This method raises the expressive power of a language model based on the matrix factorization interpretation of language modeling introduced by Yang et al. (2018). Our proposed method improves the current state-of-the-art language model and achieves the best score on the Penn Treebank and WikiText-2, which are the standard benchmark datasets. Moreover, we indicate our proposed method contributes to application tasks: machine translation and headline generation.</abstract>
<identifier type="citekey">takase-etal-2018-direct</identifier>
<identifier type="doi">10.18653/v1/D18-1489</identifier>
<location>
<url>https://aclanthology.org/D18-1489</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4599</start>
<end>4609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Direct Output Connection for a High-Rank Language Model
%A Takase, Sho
%A Suzuki, Jun
%A Nagata, Masaaki
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F takase-etal-2018-direct
%X This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also middle layers. This method raises the expressive power of a language model based on the matrix factorization interpretation of language modeling introduced by Yang et al. (2018). Our proposed method improves the current state-of-the-art language model and achieves the best score on the Penn Treebank and WikiText-2, which are the standard benchmark datasets. Moreover, we indicate our proposed method contributes to application tasks: machine translation and headline generation.
%R 10.18653/v1/D18-1489
%U https://aclanthology.org/D18-1489
%U https://doi.org/10.18653/v1/D18-1489
%P 4599-4609
Markdown (Informal)
[Direct Output Connection for a High-Rank Language Model](https://aclanthology.org/D18-1489) (Takase et al., EMNLP 2018)
ACL
- Sho Takase, Jun Suzuki, and Masaaki Nagata. 2018. Direct Output Connection for a High-Rank Language Model. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4599–4609, Brussels, Belgium. Association for Computational Linguistics.