---
_id: '21177'
abstract:
- lang: eng
  text: 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.
author:
- first_name: Maximilian
  full_name: Spliethöver, Maximilian
  id: '84035'
  last_name: Spliethöver
  orcid: 0000-0003-4364-1409
- first_name: Jonas
  full_name: Klaff, Jonas
  last_name: Klaff
- first_name: Hendrik
  full_name: Heuer, Hendrik
  last_name: Heuer
citation:
  ama: 'Spliethöver M, Klaff J, Heuer H. Is It Worth the Attention? A Comparative
    Evaluation of Attention Layers for Argument Unit Segmentation. In: <i>Proceedings
    of the 6th Workshop on Argument Mining</i>. Florence, Italy: Association for Computational
    Linguistics; 2019:74-82. doi:<a href="https://doi.org/10.18653/v1/W19-4509">10.18653/v1/W19-4509</a>'
  apa: 'Spliethöver, M., Klaff, J., &#38; Heuer, H. (2019). Is It Worth the Attention?
    A Comparative Evaluation of Attention Layers for Argument Unit Segmentation. In
    <i>Proceedings of the 6th Workshop on Argument Mining</i> (pp. 74–82). Florence,
    Italy: Association for Computational Linguistics. <a href="https://doi.org/10.18653/v1/W19-4509">https://doi.org/10.18653/v1/W19-4509</a>'
  bibtex: '@inproceedings{Spliethöver_Klaff_Heuer_2019, place={Florence, Italy}, title={Is
    It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument
    Unit Segmentation}, DOI={<a href="https://doi.org/10.18653/v1/W19-4509">10.18653/v1/W19-4509</a>},
    booktitle={Proceedings of the 6th Workshop on Argument Mining}, publisher={Association
    for Computational Linguistics}, author={Spliethöver, Maximilian and Klaff, Jonas
    and Heuer, Hendrik}, year={2019}, pages={74–82} }'
  chicago: 'Spliethöver, Maximilian, Jonas Klaff, and Hendrik Heuer. “Is It Worth
    the Attention? A Comparative Evaluation of Attention Layers for Argument Unit
    Segmentation.” In <i>Proceedings of the 6th Workshop on Argument Mining</i>, 74–82.
    Florence, Italy: Association for Computational Linguistics, 2019. <a href="https://doi.org/10.18653/v1/W19-4509">https://doi.org/10.18653/v1/W19-4509</a>.'
  ieee: M. Spliethöver, J. Klaff, and H. Heuer, “Is It Worth the Attention? A Comparative
    Evaluation of Attention Layers for Argument Unit Segmentation,” in <i>Proceedings
    of the 6th Workshop on Argument Mining</i>, Florence, Italy, 2019, pp. 74–82.
  mla: Spliethöver, Maximilian, et al. “Is It Worth the Attention? A Comparative Evaluation
    of Attention Layers for Argument Unit Segmentation.” <i>Proceedings of the 6th
    Workshop on Argument Mining</i>, Association for Computational Linguistics, 2019,
    pp. 74–82, doi:<a href="https://doi.org/10.18653/v1/W19-4509">10.18653/v1/W19-4509</a>.
  short: 'M. Spliethöver, J. Klaff, H. Heuer, in: Proceedings of the 6th Workshop
    on Argument Mining, Association for Computational Linguistics, Florence, Italy,
    2019, pp. 74–82.'
conference:
  location: Florence, Italy
  name: 6th Workshop on Argument Mining
date_created: 2021-02-04T14:41:58Z
date_updated: 2022-01-06T06:54:48Z
doi: 10.18653/v1/W19-4509
extern: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://www.aclweb.org/anthology/W19-4509/
oa: '1'
page: 74-82
place: Florence, Italy
publication: Proceedings of the 6th Workshop on Argument Mining
publication_status: published
publisher: Association for Computational Linguistics
status: public
title: Is It Worth the Attention? A Comparative Evaluation of Attention Layers for
  Argument Unit Segmentation
type: conference
user_id: '84035'
year: '2019'
...