InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
This addresses the sentence insertion challenge for NLP applications, showing incremental improvement over existing methods.
The paper tackled the sentence insertion problem in NLP by introducing InsertGNN, a hierarchical Graph Neural Network that models sentences as a graph, achieving 70% accuracy on a TOEFL dataset, matching average human performance.
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.