Search Result

Select

An Emotion-Cause Pair Extraction Model Based on Multichannel Compact Bilinear Pooling

HUANG Jin, XU Shi, CAI Ercong, WU Zhijie, GUO Meimei, ZHU Jia

Acta Scientiarum Naturalium Universitatis Pekinensis 2022, 58 (1): 21-28. DOI: 10.13209/j.0479-8023.2021.108

Abstract （509）

HTML

PDF（pc）（700KB）（110）

Save

The authors propose a model based on multichannel compact bilinear pooling to rank pair candidates in a document. The proposed model firstly extracts the emotion-specific and cause-specific representation containing position information via graph attention network, then further learns the local relation representation between emotion clause and cause clause through the local relation-aware module. Finally, these representations are fused via multichannel compact bilinear pooling to learn the emotion-cause pairs representation for effective ranking. Experimental results show that the proposed approach achieves the best performance among all compared approaches on the task.

Related Articles | Metrics | Comments（0）

Select

Syntax-based Code Generation Model with Selective Local Attention and Pre-order Information LSTM Decoder

LIANG Wanying, ZHU Jia, WU Zhijie, YAN Zhiwen, TANG Yong, HUANG Jin, YU Weihao

Acta Scientiarum Naturalium Universitatis Pekinensis 2021, 57 (1): 45-52. DOI: 10.13209/j.0479-8023.2020.086

Abstract （873）

HTML

PDF（pc）（805KB）（179）

Save

This paper proposes a syntax-based code generation model with selective local attention and a preorder information decoder based on long-short term memory (LSTM) neural network, which aims to enhance the relevance by changing the calculation scope of the context vector and fuse more pre-order information during the decoding process. Code generation experiments in two dataset Hearthstone and Django confirm the effectiveness of this model. Compared with state-of-the-art models, the proposed model not only achieves excellent accuracy and bilingual evaluation understudy score, but also minimizing computational effort.

Related Articles | Metrics | Comments（0）

Select

Ecological Security Assessment and Countermeasures of Water Environment Based on Improved Analytic Hierarchy Process: A Case Study of Xingtai City

LI Yuping, ZHU Chen, ZHANG Luxuan, WANG Yanchao, WU Zhijie, NIU Xuran

Acta Scientiarum Naturalium Universitatis Pekinensis 2019, 55 (2): 310-316. DOI: 10.13209/j.0479-8023.2018.096

Abstract （1026）

HTML

PDF（pc）（676KB）（252）

Save

Based on the improved analytic hierarchy process, the authors adopted a 3-scale (0, 1, 2) matrix method to establish regional water ecological security assessment system including 3 layers and 24 indicators according to the real conditions of water environment in Xingtai City. The ecological security assessment system could analyze the influence factors of water environmental security status and evaluate the security situation in Xingtai City. The results showed that the five top influence factors were sewage treatment rate, annual precipitation, wastewater total amount, industrial waste water discharged and urban residential domestic sewage in the 24 indicators. The composite evaluating indexes of the water environment ecological security were within the bandwidth of 0.36 to 0.63, which indicated that the water environment ecological security was still in severe with general or poor state. Some coping strategies and suggestions were put forward to water environmental safety in Xingtai City. The research would provide a theoretical basis for water resource sustainable utilization and a reference for the similar natural condition areas.

Related Articles | Metrics | Comments（0）