@inproceedings{spliethover-etal-2019-worth,
title = "Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation",
author = {Splieth{\"o}ver, Maximilian and
Klaff, Jonas and
Heuer, Hendrik},
editor = "Stein, Benno and
Wachsmuth, Henning",
booktitle = "Proceedings of the 6th Workshop on Argument Mining",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4509/",
doi = "10.18653/v1/W19-4509",
pages = "74--82",
abstract = "Attention mechanisms have seen some success for natural language processing downstream tasks in recent years and generated new state-of-the-art results. A thorough evaluation of the attention mechanism for the task of Argumentation Mining is missing. With this paper, we report a comparative evaluation of attention layers in combination with a bidirectional long short-term memory network, which is the current state-of-the-art approach for the unit segmentation task. We also compare sentence-level contextualized word embeddings to pre-generated ones. Our findings suggest that for this task, the additional attention layer does not improve the performance. In most cases, contextualized embeddings do also not show an improvement on the score achieved by pre-defined embeddings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spliethover-etal-2019-worth">
<titleInfo>
<title>Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Spliethöver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Klaff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Heuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henning</namePart>
<namePart type="family">Wachsmuth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Attention mechanisms have seen some success for natural language processing downstream tasks in recent years and generated new state-of-the-art results. A thorough evaluation of the attention mechanism for the task of Argumentation Mining is missing. With this paper, we report a comparative evaluation of attention layers in combination with a bidirectional long short-term memory network, which is the current state-of-the-art approach for the unit segmentation task. We also compare sentence-level contextualized word embeddings to pre-generated ones. Our findings suggest that for this task, the additional attention layer does not improve the performance. In most cases, contextualized embeddings do also not show an improvement on the score achieved by pre-defined embeddings.</abstract>
<identifier type="citekey">spliethover-etal-2019-worth</identifier>
<identifier type="doi">10.18653/v1/W19-4509</identifier>
<location>
<url>https://aclanthology.org/W19-4509/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>74</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation
%A Spliethöver, Maximilian
%A Klaff, Jonas
%A Heuer, Hendrik
%Y Stein, Benno
%Y Wachsmuth, Henning
%S Proceedings of the 6th Workshop on Argument Mining
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F spliethover-etal-2019-worth
%X Attention mechanisms have seen some success for natural language processing downstream tasks in recent years and generated new state-of-the-art results. A thorough evaluation of the attention mechanism for the task of Argumentation Mining is missing. With this paper, we report a comparative evaluation of attention layers in combination with a bidirectional long short-term memory network, which is the current state-of-the-art approach for the unit segmentation task. We also compare sentence-level contextualized word embeddings to pre-generated ones. Our findings suggest that for this task, the additional attention layer does not improve the performance. In most cases, contextualized embeddings do also not show an improvement on the score achieved by pre-defined embeddings.
%R 10.18653/v1/W19-4509
%U https://aclanthology.org/W19-4509/
%U https://doi.org/10.18653/v1/W19-4509
%P 74-82
Markdown (Informal)
[Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation](https://aclanthology.org/W19-4509/) (Spliethöver et al., ArgMining 2019)
ACL