Self-learning statistical natural language processing for automatic production of virtual personal assistants

Patent metadata

Field	Value
Publication number	US-9772994-B2
Application number	US-201414341013-A
Country	US
Kind code	B2
Filing date	Jul 25, 2014
Priority date	Jul 25, 2013
Publication date	Sep 26, 2017
Grant date	Sep 26, 2017

Abstract

Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.

First claim

The invention claimed is:

1. A computing device for interpreting natural language requests, the computing device comprising:
a semantic compiler module to generate a semantic model as a function of a corpus of predefined requests, wherein the semantic model includes a plurality of mappings between a natural language request and a semantic representation of the natural language request, wherein the semantic representation identifies a user intent and zero or more slots associated with the user intent; and
a request decoder module to: (i) generate, using the semantic model, a lattice of candidate alternatives indicative of a natural language request, wherein each candidate alternative represents a token of the natural language request, and wherein the lattice comprises a plurality of routes, wherein each route represents the natural language request; (ii) assign a composite confidence weight to each candidate alternative as a function of the semantic model; (iii) determine an optimal route through the candidate alternative lattice from the plurality of routes based on the composite confidence weight; and (iv) generate a semantic representation of the natural language request as a function of the candidate alternatives of the optimal route;
wherein to generate the semantic model comprises to: (i) identify a contextual semantic feature in the corpus using a semi-supervised algorithm, wherein the contextual semantic feature comprises a sequence of lexical sets associated with a user intent and zero or more slots associated with the user intent; (ii) determine a first probability of the contextual semantic feature given the user intent; and (iii) determine a normalized probability of the user intent as a function of a rate of occurrence of the contextual semantic feature in the corpus; and
wherein to identify the contextual semantic feature using the semi-supervised algorithm comprises to: (i) tag a first group of predefined sample queries in the corpus to identify user intents and slots; (ii) extract the contextual semantic feature from the sample queries; (iii) analyze, using the semantic model, a second group of predefined sample queries in the corpus; (iv) extract additional contextual semantic features in response to analyzing the second group of predefined sample queries; and (v) update the first probability and the normalized probability in response to analyzing the second group of predefined sample queries.

2. The computing device of claim 1 , wherein to identify the contextual semantic feature comprises to identify the contextual semantic feature using an unsupervised algorithm, wherein to identify the contextual semantic feature using the unsupervised algorithm comprises to:
identify predefined named entities and relationships in a first group of predefined sample queries in the corpus;
cluster the predefined sample queries using an unsupervised clustering algorithm to generate a plurality of clusters; and
assign a user intent and slots to each cluster of the plurality of clusters.

3. The computing device of claim 1 , wherein to generate the semantic model comprises to:
generate an ontological index as a function of a predefined ontology associated with the user intent, wherein the predefined ontology includes a plurality of objects describing a knowledge domain.

4. The computing device of claim 3 , wherein to generate the ontological index comprises to:
assign a vector space to an object type of the predefined ontology, wherein the vector space includes a plurality of coordinates, wherein each coordinate encodes a lexical token representing an associated object of the predefined ontology; and
map a slot of the user intent associated with the predefined ontology to the vector space.

5. The computing device of claim 1 , wherein the request decoder module is further to:
receive a representation of speech data indicative of the natural language request; and
convert the representation of speech data to a first lattice of candidate alternatives indicative of the natural language request, wherein to convert the representation of speech data comprises to convert the representation of speech data using a language model generated as a function of a domain-biased web corpus;
wherein to generate the lattice of candidate alternatives comprises to generate the lattice of candidate alternatives in response to conversion of the representation of speech data to the first lattice of candidate alternatives.

6. The computing device of claim 1 , wherein to generate the lattice comprises to:
generate a candidate alternative corresponding to a user intent and associated slots of a mapping of the semantic model; and
generate a candidate alternative using a language model, as a function of phonetic similarity to the natural language request.

7. The computing device of claim 1 , wherein to assign the composite confidence weight further comprises to assign a confidence weight as a function of a language model.

8. The computing device of claim 7 , wherein to assign the confidence weight as a function of the language model comprises to assign a phonetic similarity score, a general language model confidence score, a domain language model score, or a syntactic confidence score.

9. The computing device of claim 1 , further comprising a dialog management module to:
determine whether the semantic representation of the natural language request includes sufficient information to perform a user intent of the semantic representation;
perform the user intent in response to a determination that the semantic representation includes sufficient information;
generate a response as a function of the semantic representation;
generate a natural language representation of the response using the semantic model; and
record a user dialog session including the natural language request and the natural language representation of the response into a corpus of recorded user dialog sessions.

10. The computing device of claim 1 , further comprising a tuning module to update the semantic model in response to generating the semantic representation.

11. The computing device of claim 10 , wherein to update the semantic model comprises to:
determine the semantic representation was generated with no ambiguities;
identify a token of the natural language request that was not decoded; or
identify an ambiguous decoding of a slot of the semantic representation.

12. A method for interpreting natural language requests, the method comprising:
generating, by a computing device, a semantic model as a function of a corpus of predefined requests, wherein the semantic model includes a plurality of mappings between a natural language request and a semantic representation of the natural language request, wherein the semantic representation identifies a user intent and zero or more slots associated with the user intent;
generating, by the computing device using the semantic model, a lattice of candidate alternatives indicative of a natural language request, wherein each candidate alternative represents a token of the natural language request, and wherein the lattice comprises a plurality of routes, wherein each route represents the natural language request;
assigning, by the computing device, a composite confidence weight to each candidate alternative as a function of the semantic model;
determining, by the computing device, an optimal route through the candidate alternative lattice from the plurality of routes based on the composite confidence weight; and
generating, by the computing device, a semantic representation of the natural language request as a function of the candidate alternatives of the optimal route;
wher

Assignees

• Intel Corp

Inventors

• Karov Yael
• Breakstone Micha
• Shilon Reshef
• Keller Orgad
• Shellef Eric

Classifications

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title