@inproceedings{skurniak-etal-2018-multi,
title = "Multi-Module Recurrent Neural Networks with Transfer Learning",
author = "Skurniak, Filip and
Janicka, Maria and
Wawer, Aleksander",
editor = "Beigman Klebanov, Beata and
Shutova, Ekaterina and
Lichtenstein, Patricia and
Muresan, Smaranda and
Wee, Chee",
booktitle = "Proceedings of the Workshop on Figurative Language Processing",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-0917",
doi = "10.18653/v1/W18-0917",
pages = "128--132",
abstract = "This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection. The proposed systems are all based on variants of recurrent neural network architectures. Specifically, we explore multiple sources of information: pre-trained word embeddings (Glove), a dictionary of language concreteness and a transfer learning scenario based on the states of an encoder network from neural network machine translation system. One of the architectures is based on combining all three systems: (1) Neural CRF (Conditional Random Fields), trained directly on the metaphor data set; (2) Neural Machine Translation encoder of a transfer learning scenario; (3) a neural network used to predict final labels, trained directly on the metaphor data set. Our results vary between test sets: Neural CRF standalone is the best one on submission data, while combined system scores the highest on a test subset randomly selected from training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skurniak-etal-2018-multi">
<titleInfo>
<title>Multi-Module Recurrent Neural Networks with Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Skurniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Janicka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Wawer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Figurative Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Lichtenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chee</namePart>
<namePart type="family">Wee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection. The proposed systems are all based on variants of recurrent neural network architectures. Specifically, we explore multiple sources of information: pre-trained word embeddings (Glove), a dictionary of language concreteness and a transfer learning scenario based on the states of an encoder network from neural network machine translation system. One of the architectures is based on combining all three systems: (1) Neural CRF (Conditional Random Fields), trained directly on the metaphor data set; (2) Neural Machine Translation encoder of a transfer learning scenario; (3) a neural network used to predict final labels, trained directly on the metaphor data set. Our results vary between test sets: Neural CRF standalone is the best one on submission data, while combined system scores the highest on a test subset randomly selected from training data.</abstract>
<identifier type="citekey">skurniak-etal-2018-multi</identifier>
<identifier type="doi">10.18653/v1/W18-0917</identifier>
<location>
<url>https://aclanthology.org/W18-0917</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>128</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Module Recurrent Neural Networks with Transfer Learning
%A Skurniak, Filip
%A Janicka, Maria
%A Wawer, Aleksander
%Y Beigman Klebanov, Beata
%Y Shutova, Ekaterina
%Y Lichtenstein, Patricia
%Y Muresan, Smaranda
%Y Wee, Chee
%S Proceedings of the Workshop on Figurative Language Processing
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F skurniak-etal-2018-multi
%X This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection. The proposed systems are all based on variants of recurrent neural network architectures. Specifically, we explore multiple sources of information: pre-trained word embeddings (Glove), a dictionary of language concreteness and a transfer learning scenario based on the states of an encoder network from neural network machine translation system. One of the architectures is based on combining all three systems: (1) Neural CRF (Conditional Random Fields), trained directly on the metaphor data set; (2) Neural Machine Translation encoder of a transfer learning scenario; (3) a neural network used to predict final labels, trained directly on the metaphor data set. Our results vary between test sets: Neural CRF standalone is the best one on submission data, while combined system scores the highest on a test subset randomly selected from training data.
%R 10.18653/v1/W18-0917
%U https://aclanthology.org/W18-0917
%U https://doi.org/10.18653/v1/W18-0917
%P 128-132
Markdown (Informal)
[Multi-Module Recurrent Neural Networks with Transfer Learning](https://aclanthology.org/W18-0917) (Skurniak et al., Fig-Lang 2018)
ACL