@inproceedings{nyegaard-signori-etal-2018-ku,
title = "{KU}-{MTL} at {S}em{E}val-2018 Task 1: Multi-task Identification of Affect in Tweets",
author = "Nyegaard-Signori, Thomas and
Helms, Casper Veistrup and
Bjerva, Johannes and
Augenstein, Isabelle",
booktitle = "Proceedings of The 12th International Workshop on Semantic Evaluation",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S18-1058",
doi = "10.18653/v1/S18-1058",
pages = "385--389",
abstract = "We take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use as little external data as possible in order to preserve the task relatedness and reduce complexity. We employ multi-task learning with hard parameter sharing to exploit the relatedness between sub-tasks. As a base model, we use a standard recurrent neural network for both the classification and regression subtasks. Our system ranks 32nd out of 48 participants with a Pearson score of 0.557 in the first subtask, and 20th out of 35 in the fifth subtask with an accuracy score of 0.464.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nyegaard-signori-etal-2018-ku">
<titleInfo>
<title>KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Nyegaard-Signori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casper</namePart>
<namePart type="given">Veistrup</namePart>
<namePart type="family">Helms</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Bjerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 12th International Workshop on Semantic Evaluation</title>
</titleInfo>
<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>We take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use as little external data as possible in order to preserve the task relatedness and reduce complexity. We employ multi-task learning with hard parameter sharing to exploit the relatedness between sub-tasks. As a base model, we use a standard recurrent neural network for both the classification and regression subtasks. Our system ranks 32nd out of 48 participants with a Pearson score of 0.557 in the first subtask, and 20th out of 35 in the fifth subtask with an accuracy score of 0.464.</abstract>
<identifier type="citekey">nyegaard-signori-etal-2018-ku</identifier>
<identifier type="doi">10.18653/v1/S18-1058</identifier>
<location>
<url>https://aclanthology.org/S18-1058</url>
</location>
<part>
<date>2018-jun</date>
<extent unit="page">
<start>385</start>
<end>389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets
%A Nyegaard-Signori, Thomas
%A Helms, Casper Veistrup
%A Bjerva, Johannes
%A Augenstein, Isabelle
%S Proceedings of The 12th International Workshop on Semantic Evaluation
%D 2018
%8 jun
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F nyegaard-signori-etal-2018-ku
%X We take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use as little external data as possible in order to preserve the task relatedness and reduce complexity. We employ multi-task learning with hard parameter sharing to exploit the relatedness between sub-tasks. As a base model, we use a standard recurrent neural network for both the classification and regression subtasks. Our system ranks 32nd out of 48 participants with a Pearson score of 0.557 in the first subtask, and 20th out of 35 in the fifth subtask with an accuracy score of 0.464.
%R 10.18653/v1/S18-1058
%U https://aclanthology.org/S18-1058
%U https://doi.org/10.18653/v1/S18-1058
%P 385-389
Markdown (Informal)
[KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets](https://aclanthology.org/S18-1058) (Nyegaard-Signori et al., SemEval 2018)
ACL