Discriminative Sentence Modeling for Story Ending Prediction
This work addresses story understanding for AI systems, but it is incremental as it builds on existing neural methods for a specific benchmark.
The authors tackled the story ending prediction task by proposing Diff-Net, a neural network that models differences between endings at three semantic levels, achieving significant performance improvements on the Story Cloze Test dataset.
Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge. To tackle this task, we propose a new neural network called Diff-Net for better modeling the differences of each ending in this task. The proposed model could discriminate two endings in three semantic levels: contextual representation, story-aware representation, and discriminative representation. Experimental results on the Story Cloze Test dataset show that the proposed model siginificantly outperforms various systems by a large margin, and detailed ablation studies are given for better understanding our model. We also carefully examine the traditional and BERT-based models on both SCT v1.0 and v1.5 with interesting findings that may potentially help future studies.