MyJournals Home  

RSS FeedsEntropy, Vol. 20, Pages 439: Factoid Question Answering with Distant Supervision (Entropy)

 
 

14 june 2018 15:58:52

 
Entropy, Vol. 20, Pages 439: Factoid Question Answering with Distant Supervision (Entropy)
 




Automatic question answering (QA), which can greatly facilitate the access to information, is an important task in artificial intelligence. Recent years have witnessed the development of QA methods based on deep learning. However, a great amount of data is needed to train deep neural networks, and it is laborious to annotate training data for factoid QA of new domains or languages. In this paper, a distantly supervised method is proposed to automatically generate QA pairs. Additional efforts are paid to let the generated questions reflect the query interests and expression styles of users by exploring the community QA. Specifically, the generated questions are selected according to the estimated probabilities they are asked. Diverse paraphrases of questions are mined from community QA data, considering that the model trained on monotonous synthetic questions is very sensitive to variants of question expressions. Experimental results show that the model solely trained on generated data via the distant supervision and mined paraphrases could answer real-world questions with the accuracy of 49.34%. When limited annotated training data is available, significant improvements could be achieved by incorporating the generated data. An improvement of 1.35 absolute points is still observed on WebQA, a dataset with large-scale annotated training samples.


Del.icio.us Digg Facebook Google StumbleUpon Twitter
 
60 viewsCategory: Informatics, Physics
 
Entropy, Vol. 20, Pages 440: On a Common Misconception Regarding the de Broglie-Bohm Theory (Entropy)
Entropy, Vol. 20, Pages 438: Analysis of Cell Signal Transduction Based on Kullback-Leibler Divergence: Channel Capacity and Conservation of Its Production Rate during Cascade (Entropy)
 
 
blog comments powered by Disqus


MyJournals.org
The latest issues of all your favorite science journals on one page

Username:
Password:

Register | Retrieve

Search:

Physics

Use these buttons to bookmark us:
Del.icio.us Digg Facebook Google StumbleUpon Twitter


Valid HTML 4.01 Transitional
Copyright © 2008 - 2018 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Travel Photos Nachrichten Indigonet Finances Leer Mandarijn