Chinese structured event extraction method
A technology of event extraction and structuring, which is applied in the fields of instruments, digital data processing, and computing, to achieve the effects of high precision and recall, clear layers, and strong practicability.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0068] Example 1. "Shougang Holdings purchased about 40.78 shares." Its syntactic dependency analysis results and syntactic dependency analysis tree are as follows: figure 2 shown. The relationship between "purchase" and the parent node Root is HED, which is the core word of this sentence, and the edges between the nodes represent the syntactic dependency.
[0069] Semantic Dependency Parsing (Semantic Dependency Parsing) is used to describe the semantic dependency relationship between words, and there is a certain relationship with semantic role labeling. Semantic role labeling only focuses on the relationship between sentence predicates and their main arguments, while semantic dependency analysis not only focuses on predicates and arguments, but also on predicates and predicates, arguments and arguments, and semantic relationships within arguments. The description of is more complete and comprehensive, which belongs to deep semantic analysis.
example 2
[0070] Example 2. "The prices of fruit sources are highly differentiated." Its SDP tree such as image 3 shown. Among them, the semantic dependency relationship between the Root node and the "differentiation" node is Root.
[0071] 2. Recognition scheme for events contained in sentences
[0072] In Chinese linguistics, parallel predicates should have the same status or properties in the theory of syntactic structure. Therefore, when analyzing the syntactic dependency structure of sentences, they should be related through a certain agreed parallel symbol. LTP tools can realize The COO symbol is used in the process of syntactic dependency analysis.
example 3
[0073] Example 3. "The prices of fruit sources are highly differentiated, and Apple futures have increased positions." Figure 4 Take the DP tree of Example 3. Among them, there are 3 events ET 1 (fruit source price, differentiated,), ET 2 (Apple futures, Masukura,) and ET 3 (Apple futures, up, ). For example 3, Figure 4 Only one statement is given in which the core verbs "Differentiation" and "Masukura" are used as ET 2 The core verb of ET is 1 The child node of the core verb "differentiate", and the syntactic dependency is COO, and ET 3 The core verb "rising" is also used as ET 2 "Massacura" child node.
[0074] Through the analysis of the syntactic dependency analysis tree, three clues are found: ①The predicate of the event is generally acted by a verb; ②The event predicate in a sentence is a parent-child node and remains continuous, such as "differentiation"→"Masukura"→"rise" ; ③ The edge of the parent-child node of the event predicate is COO. According to these...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com