KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Zihao, Wang, Zhaowei, Zong, Qing, Song, Yangqiu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909272377393152
author Zheng, Zihao
Wang, Zhaowei
Zong, Qing
Song, Yangqiu
author_facet Zheng, Zihao
Wang, Zhaowei
Zong, Qing
Song, Yangqiu
contents Dialogical Argument Mining(DialAM) is an important branch of Argument Mining(AM). DialAM-2024 is a shared task focusing on dialogical argument mining, which requires us to identify argumentative relations and illocutionary relations among proposition nodes and locution nodes. To accomplish this, we propose a two-stage pipeline, which includes the Two-Step S-Node Prediction Model in Stage 1 and the YA-Node Prediction Model in Stage 2. We also augment the training data in both stages and introduce context in Stage 2. We successfully completed the task and achieved good results. Our team Pokemon ranked 1st in the ARI Focused score and 4th in the Global Focused score.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19740
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining
Zheng, Zihao
Wang, Zhaowei
Zong, Qing
Song, Yangqiu
Computation and Language
Artificial Intelligence
Dialogical Argument Mining(DialAM) is an important branch of Argument Mining(AM). DialAM-2024 is a shared task focusing on dialogical argument mining, which requires us to identify argumentative relations and illocutionary relations among proposition nodes and locution nodes. To accomplish this, we propose a two-stage pipeline, which includes the Two-Step S-Node Prediction Model in Stage 1 and the YA-Node Prediction Model in Stage 2. We also augment the training data in both stages and introduce context in Stage 2. We successfully completed the task and achieved good results. Our team Pokemon ranked 1st in the ARI Focused score and 4th in the Global Focused score.
title KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.19740