Building a Question-Answering Chatbot using Forum Data in the Semantic Space

We build a conversational agent which knowledge base is an online forum for parents of autistic children. We collect about 35,000 threads totalling some 600,000 replies, and label 1% of them for usefulness using Amazon Mechanical Turk. We train a Random Forest Classifier using sent2vec features to label the remaining thread replies. Then, we use word2vec to match user queries conceptually with a thread, and then a reply with a predefined context window.


Year:
Jun 13 2018
Publisher:
2018 SwissText Conference, June 12-13, Winterthur, Switzerland
Keywords:
Note:
Best Presentation Award at SwissText 2018, Winterthur, Switzerland
Additional link:
Laboratories:




 Record created 2018-08-13, last modified 2018-11-17

Final:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)