Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TASLP.2019.2893499 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Task analysis,Context modeling,Predictive models,Speech processing,Computational modeling,Natural languages,Semantics | Feature vector,Task analysis,Computer science,Speech recognition,Context model,Natural language,Natural language understanding,Artificial intelligence,Natural language processing,Cloze test,Semantics,Comprehension | Journal |
Volume | Issue | ISSN |
27 | 4 | 2329-9290 |
Citations | PageRank | References |
1 | 0.36 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mantong Zhou | 1 | 5 | 1.09 |
Minlie Huang | 2 | 1260 | 90.68 |
Xiaoyan Zhu | 3 | 2125 | 141.16 |