17982963. SYSTEM AND METOHD OF PERFORMING DATA TRAINING ON MORPHEME PROCESSING RULES simplified abstract (Kia Corporation)
SYSTEM AND METOHD OF PERFORMING DATA TRAINING ON MORPHEME PROCESSING RULES
Organization Name
Inventor(s)
Cheongjae Lee of Suwon-si (KR)
Junseok Kim of Seongnam-si (KR)
Hyunjoon Cheon of Incheon (KR)
SYSTEM AND METOHD OF PERFORMING DATA TRAINING ON MORPHEME PROCESSING RULES - A simplified explanation of the abstract
This abstract first appeared for US patent application 17982963 titled 'SYSTEM AND METOHD OF PERFORMING DATA TRAINING ON MORPHEME PROCESSING RULES
Simplified Explanation
The patent application describes a method for processing natural language by compressing multiple languages into a single grammar, reducing the resources and time required for analyzing input sentences. The method involves separating the input sentence into morphemes, recognizing the grammar of the sentence, and analyzing its meaning based on the recognized grammar. The recognition of grammar involves matching the input sentence with pre-stored grammars, some of which are obtained by compressing multiple grammars that share common elements.
- Method for processing natural language by compressing multiple languages into a single grammar
- Separating input sentences into morphemes
- Recognizing the grammar of the input sentence
- Analyzing the meaning of the input sentence based on the recognized grammar
- Recognition of grammar involves matching the input sentence with pre-stored grammars
- Pre-stored grammars are obtained by compressing multiple grammars with common elements
Potential Applications
- Natural language processing systems
- Machine translation
- Speech recognition
- Chatbots and virtual assistants
Problems Solved
- Reduces resources and time required for analyzing input sentences
- Enables efficient processing of multiple languages
- Improves accuracy and speed of natural language processing systems
Benefits
- Faster and more efficient analysis of natural language
- Improved accuracy in recognizing grammar and analyzing meaning
- Reduced computational resources and time required
- Enhanced performance of natural language processing systems
Original Abstract Submitted
A method of processing a natural language may include generating a grammar used for analyzing a natural language by compressing a plurality of languages including common elements so that resources and time required for recognizing a grammar of an input sentence may be reduced. The method of processing a natural language may include separating an input sentence in units of morphemes, recognizing a grammar of the input sentence separated in units of morphemes, and analyzing a meaning of the input sentence based on the recognized grammar. The recognizing of the grammar may include recognizing a grammar that matches the input sentence separated in units of morpheme from among a plurality of pre-stored grammars, and the plurality of pre-stored grammars may include at least one grammar obtained by compressing two or more grammars to which at least one element among a plurality of elements constituting a single grammar is common.