1 Hit in 7.0 sec

Incremental Improvement of a Question Answering System by Re-ranking Answer Candidates using Machine Learning [article]

Michael Barz, Daniel Sonntag
2019 arXiv   pre-print
Our contributions are: (1) we generate a QA training corpus starting from 877 answers from the customer care domain of T-Mobile Austria, (2) we implement a state-of-the-art QA pipeline using neural sentence  ...  Our re-ranking approach learns a similarity function using n-gram based features using the query, the answer and the initial system confidence as input.  ...  : Modeling Twitter Customer ServiceConversations Using Fine- Grained Dialogue Acts.  ... 
arXiv:1908.10149v1 fatcat:22p7ay66krcehdzhnqbbct5kfe