Recovering Question Answering Errors via Query Revision
| Autor: | Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
business.industry Factoid 02 engineering and technology Base (topology) computer.software_genre 03 medical and health sciences 0302 clinical medicine Component (UML) 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering Question answering 020201 artificial intelligence & image processing Artificial intelligence F1 score business computer Natural language processing |
| Zdroj: | EMNLP |
| DOI: | 10.18653/v1/d17-1094 |
| Popis: | The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes. In this work, we propose to crosscheck the corresponding KB relations behind the predicted answers and identify potential inconsistencies. Instead of developing a new model that accepts evidences collected from these relations, we choose to plug them back to the original questions directly and check if the revised question makes sense or not. A bidirectional LSTM is applied to encode revised questions. We develop a scoring mechanism over the revised question encodings to refine the predictions of a base QA system. This approach can improve the F1 score of STAGG (Yih et al., 2015), one of the leading QA systems, from 52.5% to 53.9% on WEBQUESTIONS data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|