公开(公告)号：US20140006012A1

公开(公告)日：2014-01-02

申请号：US13539674

申请日：2012-07-02

申请人： Ming Zhou ,  Furu Wei ,  Xiaohua Liu ,  Hong Sun ,  Yajuan Duan ,  Chengjie Sun ,  Heung-Yeung Shum

发明人： Ming Zhou ,  Furu Wei ,  Xiaohua Liu ,  Hong Sun ,  Yajuan Duan ,  Chengjie Sun ,  Heung-Yeung Shum

IPC分类号： G06F17/27

CPC分类号： G06F16/3329 ,  G06F16/3344 ,  G06F17/278

摘要： Techniques described enable answering a natural language question using machine learning-based methods to gather and analyze evidence from web searches. A received natural language question is analyzed to extract query units and to determine a question type, answer type, and/or lexical answer type using rules-based heuristics and/or machine learning trained classifiers. Query generation templates are employed to generate a plurality of ranked queries to be used to gather evidence to determine the answer to the natural language question. Candidate answers are extracted from the results based on the answer type and/or lexical answer type, and ranked using a ranker previously trained offline. Confidence levels are calculated for the candidate answers and top answer(s) may be provided to the user if the confidence levels of the top answer(s) surpass a threshold.

摘要翻译： 所描述的技术使用基于机器学习的方法来回答自然语言问题，以收集和分析来自网络搜索的证据。 分析收到的自然语言问题以提取查询单元，并使用基于规则的启发式和/或机器学习训练分类器来确定问题类型，答案类型和/或词汇答案类型。 采用查询生成模板来生成多个排列的查询，用于收集证据以确定自然语言问题的答案。 基于答案类型和/或词汇答案类型从结果中提取候选答案，并使用以前在线下训练的跑步者进行排名。 对于候选答案计算置信水平，如果顶级答案的置信水平超过阈值，则可以向用户提供顶级答案。