Story Ending Selection by Finding Hints From Pairwise Candidate Endings

By Mantong Zhou, Minlie Huang, Xiaoyan Zhu. 2019

12 citations recorded by the source corpus.

The ability of story comprehension is a strong indicator of natural language understanding. Recently, Story Cloze Test has been introduced as a new task of machine reading comprehension, i.e., selecting a correct ending from two candidate endings given a four-sentence story context. Most existing methods for Story Cloze Test are essentially matching-based that operate by comparing an individual ending with a given context, therefore suffering from the evidence bias issue: both candidate endings can obtain supporting evidence from the story context, which misleads the classifier to choose an incorrect ending. To address this issue, we present a novel idea to improve story comprehension by utilizing the hints that are obtained through comparing two candidate endings. The proposed model firstly anticipates a feature vector for a possible ending solely based on the context, and then refines the feature prediction using the hints which encode the difference between two candidates. The candidate ending whose feature vector is more similar to the predicted ending vector is regarded as correct. Experimental results demonstrate that our approach can alleviate the evidence bias issue and improve story comprehension.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Minlie Huang
2. Xiaoyan Zhu
3. Ting-Wei Liu
4. Xiao Ding
5. Zhongyang Li
6. Jian Guan
7. Fei Huang
8. Zhihao Zhao

In Computer Vision and Pattern Recognition

1. Minlie Huang
2. Jian Guan
3. Xiaoyan Zhu
4. Ting-Wei Liu
5. Xiao Ding
6. Zhongyang Li
7. Fei Huang
8. Jason Aaron Edward Weston

In Natural Language Processing

1. Ting-Wei Liu
2. Xiao Ding
3. Zhongyang Li
4. Minlie Huang
5. Xiaoyan Zhu
6. Fei Huang
7. Zhihao Zhao
8. Jian Guan

Citations in the corpus

• Story Ending Prediction by Transferable BERT (2019, methodology): “There have been a variety of models trying to solve SCT so far [Schwartz et al., 2017; Chaturvedi et al., 2017; Zhou et al., 2019; Li et al., 2018b].”
• A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation (2020, background): “The original task is designed to select a correct story ending from two candidates (Zhou et al., 2019), while our task is to generate a reasonable story given the first sentence of a story (i.”