Microsoft Technology Licensing, LLC

Kai-Fu Lee

Zheng Chen

Jian Han

Jianfeng Gao

Lee-Feng Chien

Hai-Feng Wang

Shuo Di

Dong-Feng Cai

Jian Wang

Mingjing Li

Chang-Ning Huang

Gao Zhang

Xianoning Ling

Qiang Yang

A language input architecture converts input strings of phonetic text to an output string of language text. The language input architecture has a search engine, one or more typing models, a language model, and one or more lexicons for different languages. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string. The language model provides probable conversion strings for each of the typing candidates based on probabilities of how likely a probable conversion output string represents the candidate string. The search engine combines the probabilities of the typing and language models to find the most probable conversion string that represents a converted form of the input string.

Language input architecture for converting one text form to another text form with tolerance to spelling typographical and conversion errors

A language input architecture receives input text (e.g., phonetic text of a character-based language) entered by a user from an input device (e.g., keyboard, voice recognition). The input text is converted to an output text (e.g., written language text of a character-based language). The language input architecture has a user interface that displays the output text and unconverted input text in line with one another. As the input text is converted, it is replaced in the UI with the converted output text. In addition to this in-line input feature, the UI enables in-place editing or error correction without requiring the user to switch modes from an entry mode to an edit mode. To assist with this in-place editing, the UI presents pop-up windows containing the phonetic text from which the output text was converted as well as first and second candidate lists that contain small and large sets of alternative candidates that might be used to replace the current output text. The language input user interface also allows a user to enter a mixed text of different languages.

Language input user interface

A language input architecture converts input strings of phonetic text to an output string of language text. The language input architecture has a search engine, typing models, a language model, and one or more lexicons for different languages. Each typing model is trained on real data, and learns probabilities of typing errors. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string. The language model provides probable conversion strings for each of the typing candidates based on probabilities of how likely a probable conversion output string represents the candidate string. The search engine combines the probabilities of the typing and language models to find the most probable conversion string that represents a converted form of the input string.

Language input architecture for converting one text form to another text form with tolerance to spelling, typographical, and conversion errors

A method for the joint optimization of language model performance and size is presented comprising developing a language model from a tuning set of information, segmenting at least a subset of a received textual corpus and calculating a perplexity value for each segment and refining the language model with one or more segments of the received corpus based, at least in part, on the calculated perplexity value for the one or more segments.

System and method for joint optimization of language model performance and size

A method is presented comprising assigning each of a plurality of segments comprising a received corpus to a node in a data structure denoting dependencies between nodes, and calculating a transitional probability between each of the nodes in the data structure.

Method and apparatus for generating and managing a language model data structure

A language input architecture converts input strings of phonetic text (e.g., Chinese Pinyin) to an output string of language text (e.g., Chinese Hanzi) in a manner that minimizes typographical errors and conversion errors that occur during conversion from the phonetic text to the language text. The language input architecture has a search engine, one or more typing models, a language model, and one or more lexicons for different languages. Each typing model is trained on real data, and learns probabilities of typing errors. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string.

Language input architecture for converting one text form to another text form with modeless entry

The generation and management of a language model data structure include assigning each segment of a received corpus to a node in a data structure that denotes dependencies between the respective nodes. A transitional probability between each of the nodes in the data structure is calculated. A frequency of occurrence is calculated for each item of the respective segments, and those nodes of the data structure associated with items that do not meet a minimum frequency of occurrence threshold are removed. The data structure may be managed across a system memory of a computer system and an extended memory of the computer system.

A method for optimizing a language model is presented comprising developing an initial language model from a lexicon and segmentation derived from a received corpus using a maximum match technique, and iteratively refining the initial language model by dynamically updating the lexicon and re-segmenting the corpus according to statistical principles until a threshold of predictive capability is achieved.

System and iterative method for lexicon, segmentation and language model joint optimization

A search engine architecture is designed to handle a full range of user queries, from complex sentence-based queries to simple keyword searches. The search engine architecture includes a natural language parser that parses a user query and extracts syntactic and semantic information. The parser is robust in the sense that it not only returns fully-parsed results (e.g., a parse tree), but is also capable of returning partially-parsed fragments in those cases where more accurate or descriptive information in the user query is unavailable. A question matcher is employed to match the fully-parsed output and the partially-parsed fragments to a set of frequently asked questions (FAQs) stored in a database. The question matcher then correlates the questions with a group of possible answers arranged in standard templates that represent possible solutions to the user query. The search engine architecture also has a keyword searcher to locate other possible answers by searching on any keywords returned from the parser. The answers returned from the question matcher and the keyword searcher are presented to the user for confirmation as to which answer best represents the user's intentions when entering the initial search query. The search engine architecture logs the queries, the answers returned to the user, and the user's confirmation feedback in a log database. The search engine has a log analyzer to evaluate the log database to glean information that improves performance of the search engine over time by training the parser and the question matcher.

Growing community of inventors

Woodinville, WA, United States of America

Kai-Fu Lee