Summary generation method and apparatus
AssigneeBeijing Baidu Netcom Science Technology Co., Ltd.
InventorsMoye Chen, Wei Xu, Jiachen Liu, Xinyan Xiao, Qiaoqiao She
Life of this patent
Estimating the term…
Abstract
Embodiments of the application disclose a summary generation method and apparatus. A specific embodiment of the method comprises: acquiring a target article including a headline and a body of the article; determining whether a question is included in the headline; determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and generating a summary of the target article based on the determined information-satisfied-paragraph. The above embodiment may generate a summary that directly satisfies the users' demand for information.
Claims12
A summary generation method comprising:
- receiving a webpage processing request from a user terminal;
- acquiring a target article including a headline and a body of the article according to the received webpage processing request;
- determining whether a question is included in the headline;
- determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline;
- and
- generating a summary of the target article based on the determined information-satisfied-paragraph, and sending the generated summary to the user terminal;
- wherein determining that the question is included in the headline comprises:
- determining that the question is included in the headline, in response to determining that the headline includes a referential relationship but does not include an object to which the referential relationship refers, and
- wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:
- deleting invalid statements included:
- the information-satisfied-paragraph, one paragraph preceding the information-satisfied-paragraph, and one paragraph following the information-satisfied-paragraph, the invalid statements comprising statements for describing pictures, statements consistent with the headline, and a header;
- and
- generating the summary based on each paragraph with the invalid statements deleted.
A summary generation apparatus comprising:
- one or more processors;
- and
- storage devices on which one or more programs are stored, when the one or more programs are executed by the one or more processors, the one or more processors are caused to,
- receive a webpage processing request from a user terminal;
- acquire a target article including a headline and a body of the article according to the received webpage processing request;
- determine whether a question is included in the headline;
- determine, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline;
- and
- generate a summary of the target article based on the determined information-satisfied-paragraph, and send the generated summary to the user terminal;
- wherein determining that the question is included in the headline comprises:
- determining that the question is included in the headline, in response to determining that the headline includes a referential relationship but does not include an object to which the referential relationship refers, and
- wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:
- deleting invalid statements included:
- the information-satisfied-paragraph, one paragraph preceding the information-satisfied-paragraph, and one paragraph following the information-satisfied-paragraph, the invalid statements comprising statements for describing pictures, statements consistent with the headline, and a header;
- and
- generating the summary based on each paragraph with the invalid statements deleted.
Dependencies are inferred from the claim text.