InsertGNN: A Hierarchical Graph Neural Network for the TOEFL Sentence Insertion Problem

Fang Wu, Stan Li


Abstract
The integration of sentences poses an intriguing challenge within the realm of NLP, but it has not garnered the attention it deserves. Existing methods that focus on sentence arrangement, textual consistency, and question answering have been shown to be inadequate in addressing this issue. To bridge this gap, we introduce InsertGNN which conceptualizes the problem as a graph and employ a hierarchical Graph Neural Network (GNN) to comprehend the interplay between sentences. Our approach was rigorously evaluated on a TOEFL dataset, and its efficacy was further validated on the expansive arXiv dataset using cross-domain learning. Thorough experimentation unequivocally establishes InsertGNN’s superiority over all comparative benchmarks, achieving an impressive 70% accuracy—a performance on par with average human test scores.
Anthology ID:
2024.findings-emnlp.9
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
173–180
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.9
DOI:
Bibkey:
Cite (ACL):
Fang Wu and Stan Li. 2024. InsertGNN: A Hierarchical Graph Neural Network for the TOEFL Sentence Insertion Problem. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 173–180, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
InsertGNN: A Hierarchical Graph Neural Network for the TOEFL Sentence Insertion Problem (Wu & Li, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.9.pdf