Prof. Feifei Xu

Co-authors

Following

Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

4 January 2023 in IEEE Transactions on Affective Computing

Journal Article

Heterogeneous Reinforcement Learning Network for Aspect-Based Sentiment Classification With External Knowledge

Aspect-based sentiment classification aims to automatically predict the sentiment polarity of the specific aspect in a text. However, it is challenging to confirm the mapping between the aspect and the core context since a number of existing methods concentrate on building the global relations of the full context rather than the partial connections based on the aspects. Motivated by the fundamental insights of reinforcement learning, we propose a novel H eterogeneous R einforcement L earning N etwork for aspect-based sentiment analysis (HRLN) to alleviate these issues, which contains two primary components, a heterogeneous network module, and a knowledge graph-based reinforcement learning module consistent with common-sense knowledge and emotional knowledge. To evaluate the effectiveness of HRLN, we conduct extensive experiments on five benchmark datasets, which indicate that HRLN achieves competitive performance and yields state-of-the-art results on all datasets. Additionally, we present an intuitive comprehension of why our HRLN model is more robust for aspect-based sentiment classification via case studies.

1 November 2020 in Journal of Physics: Conference Series

Conference Paper

Bert-based Siamese Network for Semantic Similarity

Feifei Xu

Zheng Shuting

Tian Yu

As a key technology in the field of natural language processing, text matching is widely used in many tasks such as question answering systems, search, recommendation, and advertising. Aiming at the insufficient feature extraction capabilities of traditional Siamese-based text matching methods, a fast matching method based on large-scale pre-training model BSSM (BERT based Siamese Semantic Model) is proposed. The proposed method uses a pre-training model to encode two texts separately, which interact the representation vectors of the two texts to obtain attention weights and generate new representation vectors, so that the new and old representation vectors can be pooled and aggregated, and finally two representation vectors are concatenated in some strategy and sent to the prediction layer for prediction. Experimental results on the AFQMC and LCQMC datasets show that the proposed method not only improves the accuracy rate, but also improves the computational efficiency.

1 July 2012 in Neurocomputing

Journal Article

Local CCA alignment and its applications

Lai Wei

Feifei Xu

8 April 2022

Book Chapter

Open-Domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

Feifei Xu

Shanlin Zhou

Yunpu Ma

Xinpeng Wang

Wenkai Zhang

Zhisong Li

1 January 2021 in Wireless Communications and Mobile Computing

Journal Article

Story Generation Using Knowledge Graph under Psychological States

Feifei Xu

Xinpeng Wang

Shanlin Zhou

Story generation, aiming to generate a story that people could understand easily, captures increasing researchers’ attention in recent years. However, a good story usually requires interesting and emotional plots. Previous works only consider a specific or binary emotion like positive or negative. In our work, we propose a Knowledge‐Aware Generation framework under Controllable CondItions (K‐GuCCI). The model assigns a change line of psychological states to story characters, which makes the story develop following the setting. Besides, we incorporate the knowledge graph into the model to facilitate the coherence of the story. Moreover, we investigate a metric AGPS to evaluate the accuracy of generated stories’ psychological states. Experiments exhibit that the proposed model improves over standard benchmarks, while also generating stories reliable and valid.

30 March 2024

Book Chapter

Object Category-Based Visual Dialog for Effective Question Generation

Feifei Xu

Yingchen Zhou

Zheng Zhong

Guangzhen Li

About Me

Feifei Xu is currently a Professor and Master’s Supervisor at Shanghai University of Electric Power, Shanghai, China. She received her Doctoral degree in Pattern Recognition and Intelligent Systems from Tongji University in 2009, and currently works in the Faculty of Artificial Intelligence at Shanghai University of Electric Power. In terms of scientific research projects, she has presided over one Youth Program of the National Natural Science Foundation of China and one Shanghai Chenguang Talent Program. She has applied for 13 invention patents, among which 9 have been officially authorized. As a core researcher, she has participated in 4 General Programs of the National Natural Science Foundation of China and 9 provincial and ministerial research projects, with a total research funding of over 4 million RMB. In addition, as a key technical backbone, she has participated in industrial horizontal projects cooperated with State Grid Shanghai Electric Power Company, Hangzhou Electric Power Company and other enterprises, with a total project fund exceeding 2.4 million RMB. Over the past five years, she has published more than 40 first-author academic papers, including 5 CCF top conference papers, 4 SCI-indexed articles, 3 papers in CAS Q1/Q2 journals, and 26 CCF C-class papers. She has obtained the Exclusive Best Overall Paper Award at the top CCF conference DASFAA 2022 and the Excellent Paper Award of the core journalData Acquisition and Processing (2019–2021).

Prof. Feifei Xu

Prof. Feifei Xu

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me