Story Ending Selection by Finding Hints From Pairwise Candidate Endings
العنوان: | Story Ending Selection by Finding Hints From Pairwise Candidate Endings |
---|---|
المؤلفون: | Xiaoyan Zhu, Minlie Huang, Mantong Zhou |
المصدر: | IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27:719-729 |
بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2019. |
سنة النشر: | 2019 |
مصطلحات موضوعية: | Context model, Cloze test, Acoustics and Ultrasonics, Computer science, business.industry, Feature vector, Natural language understanding, Context (language use), computer.software_genre, Comprehension, 030507 speech-language pathology & audiology, 03 medical and health sciences, Computational Mathematics, Computer Science (miscellaneous), Feature (machine learning), Artificial intelligence, Electrical and Electronic Engineering, 0305 other medical science, business, computer, Natural language processing, Natural language |
الوصف: | 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. |
تدمد: | 2329-9304 2329-9290 |
الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::0c3ea0c6b4e6bd6bdf714f49092402e9Test https://doi.org/10.1109/taslp.2019.2893499Test |
حقوق: | CLOSED |
رقم الانضمام: | edsair.doi...........0c3ea0c6b4e6bd6bdf714f49092402e9 |
قاعدة البيانات: | OpenAIRE |
تدمد: | 23299304 23299290 |
---|