NLU Argument Ordering Standardization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current natural language understanding (NLU) systems face inefficiencies in syntactic and semantic analysis, particularly in handling ambiguous natural languages and non-literal language use, and struggle to maintain context and infer communication goals in dialogues.

Innovation Solution

The implementation of a method using thematic role sequences and traveling features to translate natural language phrases into artificial language expressions, enabling standardized logic-based representations and simplifying grammar rules to reduce parse tree construction, thereby improving syntactic and semantic analysis efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional syntactic and semantic analysis methods are used in NLU systems, then the systems can process natural language inputs, but the analysis efficiency is low and the complexity of handling ambiguous language increases

Engineering Contradiction:

Improveanalysis efficiencyVSAvoidcomplexity of handling ambiguous language

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent changes the parameter of argument ordering by applying thematic role sequences that standardize the order of arguments in predicate expressions. This transformation converts variable-order natural language arguments into fixed-order standardized expressions, improving analysis efficiency while reducing complexity in handling ambiguity.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces traveling features as intermediary elements that carry thematic role information through the parse tree construction process. These features act as mediators between syntactic structure and semantic interpretation, enabling efficient handling of ambiguous language by maintaining context information throughout the analysis process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If comprehensive parse tree construction is performed to handle all possible language interpretations, then semantic accuracy is improved, but the computational time and resources increase significantly

Engineering Contradiction:

Improvesemantic accuracyVSAvoidcomputational time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-defining thematic role sequences and argument ordering rules before the actual parse tree construction. This allows the system to immediately apply standardized ordering to natural language inputs without performing exhaustive analysis of all possible interpretations, thereby maintaining semantic accuracy while reducing computational time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the language analysis process into distinct stages: thematic role assignment, argument ordering application, and parse tree construction. By separating these functions and applying argument ordering early in the process, the system achieves efficient processing while preserving semantic accuracy through structured analysis.

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If standardized logic-based representations are implemented to improve inference capability, then the ability to maintain context and infer communication goals is enhanced, but the complexity of translating natural language into standardized forms increases

Engineering Contradiction:

Improveinference capabilityVSAvoidcomplexity of translation process

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements universality by creating a standardized predicate expression format that serves multiple functions: representing syntactic structure, encoding semantic meaning, and enabling logical inference. This universal representation format reduces translation complexity by providing a single standardized target form that handles all these requirements simultaneously.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent uses traveling features as intermediaries that facilitate the translation from natural language to standardized logic-based representations. These features carry thematic role information through the translation process, making the complex translation operation manageable by breaking it into tracked, incremental transformations.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9965461B2Systems and methods for improving the efficiency of syntactic and semantic analysis in automated processes for natural language understanding using argument ordering

Publication Date: 2018.05.08 THE SOFTWARE SHOP

AI summary

A natural language understanding system may be given the capability to construct a semantically detailed parse tree for each acceptable interpretation of an input natural language expression (or fewer such parse trees than interpretations) by independently solving sub-trees corresponding to various series of post nominal modifiers and associating those partial solutions with corresponding nodes in the overall parse tree. The argument order in predicate calculus atomic formulas may be standardized in a manner that supports the use of a chart parser applied to a head-driven phase structure grammar and that permits a simplified more tractable grammar that in turn can be used as a domain general semantic grammar.