InsertGNN：图神经网络能否在TOEFL句子插入问题中超越人类？
InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
AI总结：
InsertGNN通过图神经网络在TOEFL句子插入任务中超越人类，实现70%的准确率。
摘要：
句子整合在NLP领域中提出了一个引人入胜的挑战，但这一问题并未获得应有的关注。现有方法在句子排列、文本一致性及问题回答方面的研究均不足以解决这一问题。为填补这一空白，我们引入了InsertGNN，将问题概念化为图，并采用层次化的图神经网络（GNN）来理解句子之间的相互作用。我们的方法在TOEFL数据集上进行了严格评估，并进一步在大规模arXiv数据集上通过跨领域学习验证其有效性。全面的实验无可置疑地证明了InsertGNN在所有比较基准上的优越性，达到了令人印象深刻的70%准确率，其性能与平均人类测试成绩相当。
英文摘要：
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 InsertGNN, which conceptualizes the problem as a graph and employs 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
