Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance
Abstract
Argumentative structure prediction aims to establish links between textual units and label the relationship between them, forming a structured representation for a given input text. The former task, linking, has been identified by earlier works as particularly challenging, as it requires finding the most appropriate structure out of a very large search space of possible link combinations. In this paper, we improve a state-of-the-art linking model by using multi-task and multi-corpora training strategies. Our auxiliary tasks help the model to learn the role of each sentence in the argumentative structure. Combining multi-corpora training with a selective sampling strategy increases the training data size while ensuring that the model still learns the desired target distribution well. Experiments on essays written by English-as-a-foreign-language learners show that both strategies significantly improve the model's performance; for instance, we observe a 15.8% increase in the F1-macro for individual link predictions.
Cite
@article{arxiv.2109.13067,
title = {Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance},
author = {Jan Wira Gotama Putra and Simone Teufel and Takenobu Tokunaga},
journal= {arXiv preprint arXiv:2109.13067},
year = {2021}
}
Comments
9 pages (excluding citations and appendix), 10 figures, 3 tables, the paper has been accepted (peer-reviewed) for publication at the 8th Workshop on Argument Mining (co-located with EMNLP 2021)