Toggle navigation
Home
About
About Journal
Historical Evolution
Indexed In
Awards
Reference Index
Editorial Board
Journal Online
Archive
Project Articles
Most Download Articles
Most Read Articles
Instruction
Contribution Column
Author Guidelines
Template
FAQ
Copyright Agreement
Expenses
Academic Integrity
Contact
Contact Us
Location Map
Subscription
Advertisement
中文
Journals
Publication Years
Keywords
Search within results
(((QIU Dawei[Author]) AND 1[Journal]) AND year[Order])
AND
OR
NOT
Title
Author
Institution
Keyword
Abstract
PACS
DOI
Please wait a minute...
For Selected:
Download Citations
EndNote
Ris
BibTeX
Toggle Thumbnails
Select
Chinese medical question answer matching method based on attention mechanism and character embedding
CHEN Zhihao, YU Xiang, LIU Zichen, QIU Dawei, GU Bengang
Journal of Computer Applications 2019, 39 (
6
): 1639-1645. DOI:
10.11772/j.issn.1001-9081.2018102184
Abstract
(
456
)
PDF
(1101KB)(
360
)
Knowledge map
Save
Aiming at the problems that the current word segmentation tool can not effectively distinguish all medical terms in Chinese medical field, and feature engineering has high labor cost, a multi-scale Convolutional Neural Network (CNN) modeling method based on attention mechanism and character embedding was proposed. In the proposed method, character embedding was combined with multi-scale CNN to extract context information at different scales of question and answer sentences, and attention mechanism was introduced to emphasize the interaction between question sentences and answer sentences, meanwhile the semantic relationship between the question sentence and the correct answer sentence was able to be effectively learned. Since the question and answer matching task in Chinese medical field does not have a standard evaluation dataset, the proposed method was evaluated using the publicly available Chinese Medical Question and Answer dataset (cMedQA). The experimental results show that the proposed method is superior to word matching, character matching and Bi-directional Long Short-Term Memory network (BiLSTM) modeling method, and the Top-1 accuracy is 65.43%.
Reference
|
Related Articles
|
Metrics
Select
Content sharing algorithm for device to device cache communication with minimum inner-cluster energy consumption
TONG Piao, LONG Long, HAN Xue, QIU Dawei, HU Qian
Journal of Computer Applications 2018, 38 (
6
): 1703-1708. DOI:
10.11772/j.issn.1001-9081.2017123015
Abstract
(
446
)
PDF
(941KB)(
342
)
Knowledge map
Save
The battery capacity of a terminal device is limited and the data transmission energy consumption is too large between devices in the Device to Device (D2D) cache communication, which lead to the decline of the file unloading rate. In order to solve the problem, a Caching communication content Sharing Algorithm for minimizing inner-Cluster node energy consumption (CCSA)was proposed. Firstly, the user nodes in the network were modeled as Poisson cluster process in view of the random distribution characteristics of user terminals. The unloading model was established based on the energy and communication distance of the node devices, and an adaptive cluster head selection weighting formula was designed. Secondly, the energy and distance weighted sum of nodes were traversed, and the local optimal principle of greedy algorithm was used to select cluster head node. Thus, the user node communication distance was optimized to ensure that users' energy consumption was the lowest to prolong their survival cycles, and the unloading rate of the system was improved. The experimental results show that, compared with the clustered Random cluster head (Random) and the non-clustered Energy Cost optimal (EC) energy consumption optimization algorithms, when the network energy consumption is optimal, the proposed algorithm prolongs the system survival cycle by about 60 percentage points and 72 percentage points. The proposed CCSA can improve the unloading rate and reduce the unloading energy consumption of the system.
Reference
|
Related Articles
|
Metrics