Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 6th Workshop on Argument Mining |
| Editors | Benno Stein, Henning Wachsmuth |
| Place of Publication | Florence |
| Pages | 74-82 |
| Number of pages | 9 |
| ISBN (electronic) | 9781950737338 |
| Publication status | Published - Aug 2019 |
| Event | 6th Workshop on Argument Mining, ArgMining 2019 - Florence, Italy Duration: 1 Aug 2019 → 1 Aug 2019 |
Abstract
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Arts and Humanities(all)
- Language and Linguistics
- Social Sciences(all)
- Linguistics and Language
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 6th Workshop on Argument Mining. ed. / Benno Stein; Henning Wachsmuth. Florence, 2019. p. 74-82.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Is It Worth the Attention?
T2 - 6th Workshop on Argument Mining, ArgMining 2019
AU - Spliethöver, Maximilian
AU - Klaff, Jonas
AU - Heuer, Hendrik
N1 - (c) 2019 Association for Computational Linguistics
PY - 2019/8
Y1 - 2019/8
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85102430148&partnerID=8YFLogxK
U2 - 10.18653/v1/W19-4509
DO - 10.18653/v1/W19-4509
M3 - Conference contribution
SP - 74
EP - 82
BT - Proceedings of the 6th Workshop on Argument Mining
A2 - Stein, Benno
A2 - Wachsmuth, Henning
CY - Florence
Y2 - 1 August 2019 through 1 August 2019
ER -