| 发明名称 |
IDENTIFYING SALIENT TERMS FOR PASSAGE JUSTIFICATION IN A QUESTION ANSWERING SYSTEM |
| 摘要 |
According to an aspect, a term saliency model is trained to identify salient terms that provide supporting evidence of a candidate answer in a question answering computer system based on a training dataset. The question answering computer system can perform term saliency weighting of a candidate passage to identify one or more salient terms and term weights in the candidate passage based on the term saliency model. The one or more salient terms and term weights can be provided to at least one passage scorer of the question answering computer system to determine whether the candidate passage is justified as providing supporting evidence of the candidate answer. |
| 申请公布号 |
US2016104075(A1) |
申请公布日期 |
2016.04.14 |
| 申请号 |
US201414512539 |
申请日期 |
2014.10.13 |
| 申请人 |
International Business Machines Corporation |
发明人 |
Chowdhury Md Faisal Mahbub;Gliozzo Alfio M.;Lally Adam P. |
| 分类号 |
G06N99/00;G06F17/27 |
主分类号 |
G06N99/00 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A method comprising:
training a term saliency model to identify salient terms that provide supporting evidence of a candidate answer in a question answering computer system based on a training dataset; performing term saliency weighting, by the question answering computer system, of a candidate passage to identify one or more salient terms and term weights in the candidate passage based on the term saliency model; and providing the one or more salient terms and term weights to at least one passage scorer of the question answering computer system to determine whether the candidate passage is justified as providing supporting evidence of the candidate answer. |
| 地址 |
Armonk NY US |
