Google Inc.

Yong-Gang Wang

Jun Wu

Lei Zhang

Bo Yang

Feng Hong

Tang Xi Liu

Henry Ou

Liangyi Ou

Xiliu Tang

Yinfei Zhang

Yongyan Liu

Implementations of the present disclosure provide an input method editor (IME) extension framework for extending the functionality of (IMEs). In some implementations, a user input into a user interface of an (IME) is received and is provided to a script engine. A script is selected from a plurality of scripts electronically stored in a script repository. The user input is processed through the script using the script engine to generate one or more candidates, and the one or more candidates are provided to an (IME) engine. In some implementations, a script file is received, the script file being executable by an (IME) system to generate one or more candidates based on a user input into the (IME) system. The script file is electronically stored in a central registry, the central registry including a plurality of scripts, and the plurality of scripts are published for download to and installation on a user device, the user device including the (IME) system.

Extension framework for input method editor

Systems, methods, and apparatuses including computer program products for generating a custom language model. In one implementation, a method is provided. The method includes receiving a collection of documents; clustering the documents into one or more clusters; generating a cluster vector for each cluster of the one or more clusters; generating a target vector associated with a target profile; comparing the target vector with each of the cluster vectors; selecting one or more of the one or more clusters based on the comparison; and generating a language model using documents from the one or more selected clusters.

Custom language models

Methods, systems, and apparatus, including computer program products, to identify topic words in a collection of documents that includes topic documents related to a topic are disclosed. A reference topic word divergence value based on a document collection and the topic document collection is determined. A candidate topic word divergence value for a candidate topic word is determined based on the document collection and the topic document collection. The candidate topic word is determined to be a topic word if the candidate topic word divergence value is greater than the reference topic word divergence value.

Domain dictionary creation by detection of new topic words using divergence value comparison

Growing community of inventors

Beijing, China

Yong-Gang Wang