Event detection method and device based on hybrid attention network
A technology of event detection and attention, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as low accuracy, limited method performance, low recall rate, etc., to alleviate data sparsity and natural language ambiguity , improve the effect of the effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0046]Example one
[0047]Such asfigure 1 As shown, an event detection method based on a hybrid attention network, the method includes:
[0048]Step 1. Construct a hybrid attention network model, including a multi-language presentation layer, a hybrid attention layer and a classification layer;figure 2 Shown
[0049]Step 2: Perform translation of the source text and acquisition of target text in multiple languages in the multilingual presentation layer, and perform text alignment to convert the target text in multiple languages into a vector representation of a sentence sequence;
[0050]Step 3. At the hybrid attention layer, concurrently conduct contextual attention learning for texts in multiple languages at the same time, and perform cross-source language and multiple target language information fusion through a multilingual attention mechanism;
[0051]Step 4. Perform predictive classification of event types at the classification layer.
[0052]The following will introduce the entire model ...
Example Embodiment
[0082]Example two
[0083]The invention also discloses an electronic device, including:
[0084]processor;
[0085]And, a memory is used to store executable instructions of the processor;
[0086]Wherein, the processor is configured to execute the aforementioned event extraction method by executing the executable instruction.
[0087]In order to evaluate the effectiveness of HAN's use of multilingual clues to improve the effect of event detection, English is used as the source language in this embodiment, and it is performed on two benchmark data sets, ACE2005 and TAC KBP 2015 event block detection evaluation data set (KBPEval2015) experiment. For the ACE2005 data set, use the same experimental settings as the previous experiments, that is, 529 / 30 / 40 documents are used as the training set / development set / test set. For the KBPEval2015 data set, we test the model on the provided evaluation data set (LDC2015R26), using the previous RichERE labeled data set (LDC2015E73) as the training set, except for...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap