17735700. METHOD OF NATURAL LANGUAGE PROCESSING BY PERFORMING SEMANTIC ANALYSIS USING SYNTACTIC INFORMATION, AND AN APPARATUS FOR THE SAME simplified abstract (Samsung Electronics Co., Ltd.)
METHOD OF NATURAL LANGUAGE PROCESSING BY PERFORMING SEMANTIC ANALYSIS USING SYNTACTIC INFORMATION, AND AN APPARATUS FOR THE SAME
Organization Name
Inventor(s)
Suhel Jaber of San Jose CA (US)
METHOD OF NATURAL LANGUAGE PROCESSING BY PERFORMING SEMANTIC ANALYSIS USING SYNTACTIC INFORMATION, AND AN APPARATUS FOR THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 17735700 titled 'METHOD OF NATURAL LANGUAGE PROCESSING BY PERFORMING SEMANTIC ANALYSIS USING SYNTACTIC INFORMATION, AND AN APPARATUS FOR THE SAME
Simplified Explanation
The patent application describes a method for enhancing natural language understanding by incorporating syntactic information. Here are the key points:
- The method involves parsing a written or spoken sentence into a syntactic tree.
- Each word in the sentence is encoded using a deep-learning network.
- A graph-based neural network is used to encode the syntactic subtree for each word.
- The encoded word and its corresponding syntactic subtree are fused together.
- The fused encodings are then used by a semantic neural network to perform various semantic tasks.
Potential applications of this technology:
- Natural language processing systems
- Virtual assistants and chatbots
- Sentiment analysis and opinion mining
- Information retrieval and question answering systems
Problems solved by this technology:
- Enhances the accuracy and performance of natural language understanding systems.
- Improves the understanding of complex sentence structures.
- Enables better interpretation of the relationships between words in a sentence.
Benefits of this technology:
- More accurate and reliable natural language understanding.
- Enhanced ability to handle complex sentence structures.
- Improved interpretation of the meaning and context of words in a sentence.
Original Abstract Submitted
A method for performing one or more natural language understanding semantic tasks augmented with syntactic information includes parsing a written or spoken utterance comprising a plurality of tokens into a full syntactic tree for the utterance; encoding each token in the utterance using a word encoder based on deep-learning network; encoding using a graph-based neural network, for each token, a syntactic subtree in which the token is a head; fusing each encoded token with the encoded syntactic subtree corresponding to that encoded token; and providing the fused encodings to a semantic neural network for performing one or more semantic tasks.
