Microsoft Technology Licensing, LLC

Other

David Neal Weise

Michael V Calcagno

Aravind Bala

Sonja Sabina Knoll

Kevin William Humphreys

Ralph A Lipe

William Ramsey

George M Moore

Raymond Edward Endres

Saliha Azzam

Stuart Raymond Patrick

David J D'Souza

Kevin Roland Powell

Amit Chatterjee

David Parkinson

Neil W Konzen

Pär Jonas Barklund

Dennis Richard Adler

Evelyne Viegas

H Gunter Zieber

A method is provided for forming a reconstructed parse structure for an initial parse structure. Under the method, at least one rule used to form the initial parse structure and at least one additional rule are executed to form the reconstructed parse structure. In many embodiments, the reconstructed parse structure differs from the initial parse structure in that a node is located in a different position in the reconstructed parse structure than in the initial parse structure.

Method and apparatus for reattaching nodes in a parse structure

A natural language parse ranker of a natural language processing (NLP) system employs a goodness function to rank the possible grammatically valid parses of an utterance. The goodness function generates a statistical goodness measure (SGM) for each valid parse The parse ranker orders the parses based upon their SGM values. It presents the parse with the greatest SGM value as the one that most likely represents the intended meaning of the speaker. The goodness function of this parse ranker is highly accurate in representing the intended meaning of a speaker. It also has reasonable training data requirements. With this parse ranker, the SGM of a particular parse is the combination of all of the probabilities of each node within the parse tree of such parse. The probability at a given node is the probability of taking a transition ('grammar rule') at that point. The probability at a node is conditioned on highly predicative linguistic phenomena, such as 'phrase levels,' &#x201c;null transitions,&#x201d; and &#x201c;syntactic history&#x201d;

Ranking parser for a natural language processing system

A method and parser are provided that generate a score for a node identified during a parse of a text segment. The score is based on a mutual information score that measures the mutual information between a phrase level for the node and a word class of at least one word in the text segment.

Method and apparatus for parsing text using mutual information

A natural language parse ranker of a natural language processing (NLP) system employs a goodness function to rank the possible grammatically valid parses of an utterance. The goodness function generates a statistical goodness measure (SGM) for each valid parse. The parse ranker orders the parses based upon their SGM values. It presents the parse with the greatest SGM value as the one that most likely represents the intended meaning of the speaker. The goodness function of this parse ranker is highly accurate in representing the intended meaning of a speaker. It also has reasonable training data requirements. With this parse ranker, the SGM of a particular parse is the combination of all of the probabilities of each node within the parse tree of such parse. The probability at a given node is the probability of taking a transition ('grammar rule') at that point. The probability at a node is conditioned on highly predicative linguistic phenomena, such as 'phrase levels,' &#x201c;null transitions,&#x201d; and &#x201c;syntactic history&#x201d;.

The present invention is a named entity (NE) interface to a linguistic analysis layer. The interface exposes each input sentence to the NE recognizers of all applications and returns all recognized NEs. Thus, the present invention can accommodate NEs which dynamically change in the applications, because each input string will be handed to the applications for NE recognition. The present invention also includes a data structure which is a normalized form of recognized NEs.

Named entity (NE) interface for multiple client application programs

A system for developing semantic schema for natural language processing has a semantic runtime engine and a semantic authoring tool. The semantic runtime engine is adapted to map a natural language input to a semantic schema and to return the mapped results to an application domain. The semantic authoring tool is adapted to receive user input for defining the semantic schema and to interact with the semantic runtime engine to test the semantic schema against a query.

Semantic authoring, runtime and training environment

A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.

Statistically driven sentence realizing method and apparatus

A method and grammar checking system are provided that generate a stochastic score, or a statistical goodness measure, for each of an input string of text and one or more alternative strings of text. An alternative generator generates the alternative strings of text, and a ranking parser produces parse trees and corresponding statistical goodness measures for each of the strings. The string of text having the highest goodness measure is selected for recommendation to a user.

Method and apparatus for improved grammar checking using a stochastic parser

A method of calculating trigram path probabilities for an input string of text containing a multi-word-entry (MWE) or a factoid includes tokenizing the input string to create a plurality of parse leaf units (PLUs). A PosColumn is constructed for each word, MWE, factoid and character in the input string of text which has a unique first (Ft) and last (Lt) token pair. TrigramColumns are constructed which define corresponding TrigramNodes each representing a trigram for three PosColumns. Forward and backward trigram path probabilities are calculated for each separate TrigramNode. The sums of all trigram path probabilities through each PLU are then calculated as a function of the forward and backward trigram path probabilities. Systems and computer-readable medium configured to implement the methods are also provided.

Method and apparatus for providing improved HMM POS tagger for multi-word entries and factoids

A natural language parse ranker of a natural language processing (NLP) system employs a goodness function to rank the possible grammatically valid parses of an utterance. The goodness function generates a statistical goodness measure (SGM) for each valid parse. The parse ranker orders the parses based upon their SGM values. It presents the parse with the greatest SGM values as the one that most likely represents the intended meaning of the speaker. The goodness function of this parse ranker is highly accurate in representing the intended meaning of a speaker. It also has reasonable training data requirements. With the parse ranker, the SGM of a particular parse is the combination of all of the probabilities of each node within the parse tree of such parse. The probability at a given node is the probability of taking a transition ('grammar rule') at that point. The probability at a node is conditioned on highly predicative linguistic phenomena, such as 'phrase levels,' &#x201c;null transitions,&#x201d; and &#x201c;syntactic history&#x201d;.

An improved natural language parser uses a template set to identify predefined parse conditions and to implement responsive actions, thus reducing processing time while increasing parse tree accuracy. The template set is used to identify predefined conditions of the current parse state, an input span, and the history of the parse process. Once a template has been matched, the improved parser implements associated responsive actions to reduce the parse time typically associated with parsing an input span under the identified conditions. This on-the-fly implementation of responsive actions permits the parser to focus the parse process on the portions of the input span most likely to generate the complete and accurate parse in the shortest amount of time.

Growing community of inventors

Kirkland, WA, United States of America

David Neal Weise