Discriminative Sentence Modeling for Story Ending Prediction

Abstract

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.

8 pages, accepted as a conference paper at AAAI 2020

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• On the difficulty of training Recurrent Neural Networks
• Teaching Machines to Read and Comprehend
• NLTK: The Natural Language Toolkit
• Bidirectional Attention Flow for Machine Comprehension
• Highway Networks
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Neural Sentence Ordering
• Consensus Attention-based Neural Networks for Chinese Reading Comprehension

Cited by in corpus (4)

• A Study of Situational Reasoning for Traffic Understanding
• GraphPlan: Story Generation by Planning with Event Graph
• Toward Better Storylines with Sentence-Level Language Models
• Sentence Semantic Regression for Text Generation