TY - GEN
T1 - EDU-AP
T2 - 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2022
AU - Saha, Sougata
AU - Das, Souvik
AU - Srihari, Rohini
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Neural approaches to end-to-end argument mining (AM) are often formulated as dependency parsing (DP), which relies on token-level sequence labeling and intricate post-processing for extracting argumentative structures from text. Although such methods yield reasonable results, operating solely with tokens increases the possibility of discontinuous and overly segmented structures due to minor inconsistencies in token level predictions. In this paper, we propose EDU-AP, an end-to-end argument parser, that alleviates such problems in dependency-based methods by exploiting the intrinsic relationship between elementary discourse units (EDUs) and argumentative discourse units (ADUs) and operates at both token and EDU level granularity. Further, appropriately using contextual information, along with optimizing a novel objective function during training, EDU-AP achieves significant improvements across all four tasks of AM compared to existing dependency-based methods.
AB - Neural approaches to end-to-end argument mining (AM) are often formulated as dependency parsing (DP), which relies on token-level sequence labeling and intricate post-processing for extracting argumentative structures from text. Although such methods yield reasonable results, operating solely with tokens increases the possibility of discontinuous and overly segmented structures due to minor inconsistencies in token level predictions. In this paper, we propose EDU-AP, an end-to-end argument parser, that alleviates such problems in dependency-based methods by exploiting the intrinsic relationship between elementary discourse units (EDUs) and argumentative discourse units (ADUs) and operates at both token and EDU level granularity. Further, appropriately using contextual information, along with optimizing a novel objective function during training, EDU-AP achieves significant improvements across all four tasks of AM compared to existing dependency-based methods.
UR - https://www.scopus.com/pages/publications/85177824649
U2 - 10.18653/v1/2022.sigdial-1.19
DO - 10.18653/v1/2022.sigdial-1.19
M3 - Conference contribution
AN - SCOPUS:85177824649
T3 - SIGDIAL 2022 - 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
SP - 183
EP - 192
BT - SIGDIAL 2022 - 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
Y2 - 7 September 2022 through 9 September 2022
ER -