Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a plurality of word strings in a first language, each received word string comprising a plurality of words, identifying one or more named entities in each received word string using a statistical classifier that was trained using training data comprising a plurality of features, wherein one of the features is a word shape feature that comprises a respective token for each letter of a respective word wherein each token signifies a case of the letter or whether the letter is a digit, and translating the received word strings from the first language to a second language including preserving the respective identified named entities in each received word string during translation.

Abstract: A method, a system, and an article are provided for automatically posting answers to questions generated by users of a chat room. In one example, a set of chat messages is used to develop a database of question and answer pairs. When a subsequent chat message is identified as being similar or identical to a question in the database, the corresponding answer to the question can be retrieved from the database and posted in the chat room.

Abstract: Implementations of the present disclosure are directed to a method, a system, and an article for suggesting emojis in electronic communication. An example method can include: providing a trie data structure on a client device, the trie data structure storing a dictionary and including a plurality of nodes, wherein at least one node in the trie data structure includes a children array including at least one of: an integer index for identifying a child node; and an array size corresponding to a number of child nodes for the at least one node; and detecting, by the client device, at least one character entered by a user in a user interface of the client device; identifying, using the trie data structure, at least one emoji corresponding to the at least one character; and presenting the at least one emoji in the user interface for user selection.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a message authored by a user, determining, using a first classifier, that the message contains at least a first word describing positive or negative sentiment and, based thereon, extracting, using a first feature extractor, one or more features of the message, wherein each feature comprises a respective word or phrase in the message and a respective weight signifying a degree of positive or negative sentiment, and determining, using a second classifier that uses the extracted features as input, a score describing a degree of positive or negative sentiment of the message, wherein the first feature extractor was trained with a set of training messages that each was labeled as having positive or negative sentiment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a plurality of word strings in a first language, each received word string comprising a plurality of words, identifying one or more named entities in each received word string using a statistical classifier that was trained using training data comprising a plurality of features, wherein one of the features is a word shape feature that comprises a respective token for each letter of a respective word wherein each token signifies a case of the letter or whether the letter is a digit, and translating the received word strings from the first language to a second language including preserving the respective identified named entities in each received word string during translation.

Abstract: Implementations of the present disclosure are directed to a method, a system, and an article for suggesting emoji for insertion into a communication having text or other content. A plurality of features corresponding to the communication are obtained and provided to a plurality of emoji detection modules. A set of emoji and first confidence scores are received from each emoji detection module and provided to at least one classifier. A proposed set of candidate emoji and second confidence scores are received from the at least one classifier. A candidate emoji is inserted into the communication.