National University of Defense Technology

Xueshan Luo

Fei Cai

Deke Guo

Honghui Chen

Lailong Luo

Wanyu Chen

Aimin Luo

Tao Chen

Dengfeng Liu

Zhen Shu

Jianming Zheng

Guoming Tang

Siyuan Wang

Hao Yuan

Peihong Li

Junxian Liu

Xinyi Li

Shixian Liu

A method and apparatus for training a few-shot event detection model based on multilingual prompt learning are provided, which includes: acquiring a training data set, applying a multilingual prompt model to any instance to obtain a predicted probability distribution of a trigger tag, so as to obtain a first loss; generating a contrastive instance and a bilingual instance, and performing multilingual prompt and cross-lingual encoding according to the input instance and the bilingual instance by applying the multilingual prompt model to obtain joint event characterization; performing event tag prediction on the joint event characterization by applying a two-level hierarchical prototype network model, and calculating a second loss; performing contrastive learning on respective instances by applying a quaternary contrastive learning module to obtain a third loss; determining a total loss of the few-shot event detection model according to respective losses, and performing model training optimization based on the total loss.

Method and apparatus for training few-shot event detection model based on multilingual prompt learning

The invention discloses a device and text representation method applied to sentence embedding, which has determining a parent word and a child words set corresponding to the parent word, obtaining an hidden interaction state of parent word based on the hidden interaction state of all child words; obtaining parent word sequence corresponding to the parent word and obtaining hidden state sequence corresponding to the hidden state of parent word; obtaining the interaction representation sequence of each parent word and other parent word based on the hidden state sequence, generating sentence embeddings. The invention proposes to realize sentence embeddings through a two-level interaction representation. The two-level interaction representation is local interaction representation and a global interaction representation respectively, and combines the two-level representation to generate a hybrid interaction representation, which can improve the accuracy and efficiency of sentence embeddings and be significantly better than the Tree-LSTM model in terms of accuracy.

Device and text representation method applied to sentence embedding

The present disclosure relates to an online task dispatching and scheduling system. The system includes an end device; an access point (AP) configured to receive a task from the end device; one or more edge servers configured to receive the task from the AP, the one or more edge servers including a task waiting queue, a processing pool, a task completion queue, and a scheduler, wherein the AP further includes a dispatcher utilizing Online Learning (OL) for determining a real-time state of network conditions and server loads; and the AP selects a target edge server from the one or more edge servers to which the task is to be dispatched; and wherein the scheduler utilizes Deep Reinforcement Learning (DRL) in generating a task scheduling policy for the one or more edge servers.

Online task dispatching and scheduling system and method thereof

Growing community of inventors

Hunan, China

Xueshan Luo