EMNLP Findings2024
InsertGNN: A Hierarchical Graph Neural Network for the TOEFL Sentence Insertion Problem
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 are inadequate in addressing this issue. To bridge this gap, we introduce Insert-GNN 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on4
- Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise OrderingsShaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou et al.EMNLP 2021 · 5 citations
- Sentence Ordering with a Coherence VerifierSainan Jia, Wei Song, Jiefu Gong, Shijin Wang et al.ACL Findings 2023 · 4 citations
- Non-Autoregressive Sentence OrderingYi Bin, Wenhao Shi, Bin Ji, Jipeng Zhang et al.EMNLP Findings 2023 · 2 citations
- Global-Local GCN: Large-Scale Label Noise Cleansing for Face RecognitionYaobin Zhang, Weihong Deng, Mei Wang, Jiani Hu et al.CVPR 2020
Related papers
- Neural Sentence Ordering Based on Constraint GraphsYutao Zhu, Kun Zhou, Jian-Yun Nie, Shengchao Liu et al.AAAI 2021 · 24 citations
- ComQA: Compositional Question Answering via Hierarchical Graph Neural NetworksBingning Wang, Ting Yao, Weipeng Chen, Jingfang Xu et al.WWW 2021 · 6 citations
- Let's Ask GNN: Empowering Large Language Model for Graph In-Context LearningZhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang et al.EMNLP Findings 2024 · 7 citations
- HEGEL: Hypergraph Transformer for Long Document SummarizationHaopeng Zhang, Xiao Liu, Jiawei ZhangEMNLP 2022 · 33 citations
- Hierarchical Graph Network for Multi-hop Question AnsweringYuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai et al.EMNLP 2020 · 157 citations
