Chinese event factuality recognition method and system
A recognition method, factual technology, applied in the direction of unstructured text data retrieval, special data processing applications, instruments, etc., can solve problems such as lack of applicability, low accuracy, high cost, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0175] example 1: Prosecutors worry [Level: Possibly] She possible [Tense: None, Level: Possibly] Really that's it Do not I have returned to Taiwan, and I am currently trying to grasp Zhu Wanqing's whereabouts through the personnel stationed abroad and international cooperation.
[0176]
[0177] As shown in Example 1, the event sentence modality (the Modality attribute of the event node) is extracted as "Other", and the event sentence tense (the Tense attribute of the event node) is "Unspecified";
[0178] Then, the event source (souce node) of the extracted event is "police inspector", the event selection predicate (event_selecting_predicates node) is "worried", and its level (event_selecting_predicates node LEVEL attribute) is "possible";
[0179] Finally, the degree word (degree node) of the extracted event is "possible", its level (degree node LEVEL attribute) is "possible", its tense (degree node TENSE attribute) is "none", and the negative word (negative_word n...
example 2
[0181] Example 2: Modality: Other / Tense: Unspecified / Source: Police Officer / ESP_Word: Concerned / ESP_Level: Possible / Degree_Word: Possible / Degree_Level: Possible / Degree_Tense=none / Negative: Not / Facutuality: May not happen.
example 3
[0182] Example 3: Modality: Other / Tense: Unspecified / Source: Police Prosecutor / ESP_Word: Worry / ESP_Level: Possible / Degree_Word: Possible / Degree_Level: Possible / Degree_Tense=none / Negative: No.
[0183] S20, on the tagged corpus, for the factual related information of each Chinese event, use the method of rules to process, transform and fuse the features, obtain a series of factual related features, and then add the real factuality of the event, and then Construct a collection of labeled corpus features;
[0184] On the test corpus, for the factual related information of each Chinese event, use the same rule method to process, transform and fuse the features to obtain a series of factual related features, and then construct the test corpus feature set.
[0185] Among them, such as image 3 As shown, the specific process of S20 is as follows:
[0186] S201, event sentence feature processing, selecting the event sentence modality and temporal information to which each event belo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


