Event atlas construction system and method based on multi-dimensional feature fusion and dependency syntax
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A multi-dimensional feature and dependency syntax technology, applied in the field of electronic information, can solve problems such as ignoring the importance of spatial relationships, imperfect evaluation methods, and single relationships between events
Active Publication Date: 2020-08-25
XI AN JIAOTONG UNIV
View PDF4 Cites 52 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005]
Second, the relationship between events is single, and most studies only focus on causal or temporal relationships.
However, existing research often ignores the importance of spatial relationships and deep semantic relationships;
[0006]
The third is that the influence of the relationship between events and events on the construction of event graphs is not considered at the same time, and the existing research o
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0165] At around 14:28 on May 12, 2008, an earthquake with a magnitude of 7.8 occurred in Wenchuan County.
[0166] After module 1 event extraction, a structured event is obtained, and the time element, location element, and trigger word of the event can be obtained, while The elements of time and place are the basis of temporal relationship extraction and spatial relationship extraction between events. Due to the uniqueness of news expression, the elements of time and place may be incomplete or inconsistent. Time serialization and locations are standardized by provinces and municipalities through event correction, which facilitates the extraction of temporal and spatial relations. In this embodiment, after event correction Enhanced structured event .
Embodiment 2
[0168] After the earthquake in Wenchuan County, Sichuan Province on May 12, 2008, it had a certain impact on Zhaotong, Yunnan and other places, and some houses have collapsed.
[0169]Events are obtained after module 1 event extraction, event1, event2.
[0170] Event1, event2. The event in Embodiment 1 can be aligned with event1 in Embodiment 2 through event alignment.
[0171] After module 3, the timing relationship can be extracted, .
[0172] After passing module 4, the first-order implicit causality can be extracted, .
[0173] Through the enhanced structured events obtained by the above modules and the multi-dimensional relationship between events, the event graph can be constructed. Such as Figure 4 and Figure 5 .
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses an event atlas construction system and method based on multi-dimensional feature fusion and dependency syntax. The event graph construction method based on multi-dimensional feature fusion and dependency syntax is realized through joint learning of event extraction, event correction and alignment based on multi-dimensional feature fusion, relationship extraction based on enhanced structured events, causal relationship extraction based on dependency syntax and graph attention network and an event graph generation module. According to the event graph construction method and device, the event graph is constructed through the quintuple information of the enhanced structured events and the relations between the events in four dimensions, and the defects that in the priorart, event representation is simple and depends on an NLP tool, the event relation is single, and the influence of the relations between the events on event graph construction is not considered at the same time are overcome. According to the event atlas construction method provided by the invention, the relationships among the events in four dimensions can be randomly combined according to different downstream tasks, and the structural characteristics of the event atlas are learned to be associated with potential knowledge, so that downstream application is assisted.
Description
【Technical field】 [0001] The invention belongs to the technical field of electronic information, and relates to a system and method for constructing event graphs based on multidimensional feature fusion and dependency syntax. 【Background technique】 [0002] The knowledge graph technology in the era of big data connects and stores massive amounts of information in structured "entity-relationship-entity" triples, so that massive unstructured and semi-structured information in the network can be effectively organized and constituted. It has achieved outstanding application effects in related fields such as justice, finance, and emergencies, and has become one of the important directions of artificial intelligence applications. However, with the growth of business needs, the entities and the relationship between entities described in traditional knowledge graphs can no longer meet the needs of different intelligent systems for knowledge reasoning and services. On the one hand, ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.