International Business Machines Corporation

Other

Guo Yu Tang

Jian Min Jiang

Guo Tong Xie

Yuan Ni

Shi Wan Zhao

Zhong Su

Shiwan Zhao

Yong Chen

Ke Ke Cai

Hong Lei Guo

Chang Hua Sun

Yufen Zhao

Ning Zhou

Liming Hu

Methods, systems, and computer program products are provided for language entity identification. In one embodiment, a computer-implemented method is disclosed. In the method, respective pinyin codes may be determined for respective Chinese characters comprised in a string that is to be processed. Then, respective pinyin features may be generated from the respective pinyin codes. Next, a candidate language entity may be identified from the string based on the respective pinyin features and a mapping describing an association between pinyin features and language entity. In other embodiments, a computer-implemented system and a computer program product for security management are disclosed.

Language entity identification

Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Automatic answer rephrasing based on talking style

Embodiments of the invention provide a computer-implemented method, computing system and computer program product for analyzing a message in a social network. The method comprises identifying an entity from the message; detecting historical popularity of the entity in a social network; identifying a topic from the message; detecting historical popularity of the topic in the social network; and generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic. Results obtained with embodiments of the invention may be provided to popularity prediction tools for improving popularity prediction of messages in social networks.

Analyzing messages in social networks

A synthesis method of alanyl-glutamine includes the steps of: The N-terminal protected alanine reacts with triphenylphosphine and hexachloroethane in organic solvent to form active ester, the active ester reacts with glutamine in a solution mixture containing organic solvent and aqueous solution of inorganic base, the resultant mixture is acidified with inorganic acid, and then the N-terminal protecting group is removed. In this method, the raw materials are cheap, the synthesis technique is simple, no disposals of separation and purification are needed, the product is easy to be separated and purified, the toxicities of all the reagents used in the course of production are minimal, it is advantageous to environment protection.

Synthesis method of alanylglutamine

Growing community of inventors

Beijing, China

Guo Yu Tang