Linmei Hu

Prof. Linmei Hu


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
30 August 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
Linmei HuLinmei Hu
Linmei Hu
ZLZeyi Liu
Zeyi Liu
ZZZiwang Zhao
Ziwang Zhao
LHLei Hou
Lei Hou
LNLiqiang Nie
Liqiang Nie
JLJuanzi Li
Juanzi Li
Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). However, though PLMs with huge parameters can effectively possess rich knowledge learned from massive training text and benefit downstream tasks at the fine-tuning stage, they still have some limitations such as poor reasoning ability due to the lack of external knowledge. Research has been dedicated to incorporating knowledge into PLMs to tackle these issues. In this paper, we present a comprehensive review of Knowledge Enhanced Pre-trained Language Models (KE-PLMs) to provide a clear insight into this thriving field. We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP. For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG), and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods. Finally, we point out some promising future directions of KE-PLMs.

11 April 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
YCYong Chen
Yong Chen
XGXinkai Ge
Xinkai Ge
SYShengli Yang
Shengli Yang
Linmei HuLinmei Hu
Linmei Hu
JLJie Li
Jie Li
JZJinwen Zhang
Jinwen Zhang
As an essential part of artificial intelligence, a knowledge graph describes the real-world entities, concepts and their various semantic relationships in a structured way and has been gradually popularized in a variety practical scenarios. The majority of existing knowledge graphs mainly concentrate on organizing and managing textual knowledge in a structured representation, while paying little attention to the multimodal resources (e.g., pictures and videos), which can serve as the foundation for the machine perception of a real-world data scenario. To this end, in this survey, we comprehensively review the related advances of multimodal knowledge graphs, covering multimodal knowledge graph construction, completion and typical applications. For construction, we outline the methods of named entity recognition, relation extraction and event extraction. For completion, we discuss the multimodal knowledge graph representation learning and entity linking. Finally, the mainstream applications of multimodal knowledge graphs in miscellaneous domains are summarized.
1

22 December 2022 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
Linmei HuLinmei Hu
Linmei Hu
ZCZiwei Chen
Ziwei Chen
ZZZiwang Zhao
Ziwang Zhao
JYJianhua Yin
Jianhua Yin
LNLiqiang Nie
Liqiang Nie
Multi-modal fake news detection has drawn considerable attention with the development of online social media. Existing methods primarily conduct direct cross-modal fusion, while ignoring the image-text matching degree which may introduce unexpected bias. This work studies an unexplored problem in multi-modal fake news detection - how to deconfound and leverage the image-text matching bias to improve the performance of fake news detection. The key lies in two aspects: how to remove the confounding effect of the image-text matching bias during training, and how to utilize the bias in the inference stage since the news with mismatched image and text is more likely to be fake. To achieve our goal, we formulate the fake news detection task as a causal graph that reflects the cause-effect factors, and propose a novel framework - C ausal Inference for L everaging I mage-text M atching B ias ( CLIMB ) in multi-modal fake news detection. To our best knowledge, this is the first work that considers the image-text matching degree into the fake news detection task with the approach of causal inference. CLIMB can be applied to any fake news detection models with visual and textual features as inputs. Extensive experiments on two real-world datasets validate the effectiveness of CLIMB.

8 January 2016 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
CSChao Shao
Chao Shao
Linmei HuLinmei Hu
Linmei Hu
JLJuan-Zi Li
Juan-Zi Li
ZWZhi-Chun Wang
Zhi-Chun Wang
TCTonglee Chung
Tonglee Chung
JXJun-Bo Xia
Jun-Bo Xia

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
Linmei HuLinmei Hu
Linmei Hu
HHHongyu He
Hongyu He
DWDuokang Wang
Duokang Wang
ZZZiwang Zhao
Ziwang Zhao
YSYingxia Shao
Yingxia Shao
LNLiqiang Nie
Liqiang Nie
Personality detection aims to detect one's personality traits underlying in social media posts. One challenge of this task is the scarcity of ground-truth personality traits which are collected from self-report questionnaires. Most existing methods learn post features directly by fine-tuning the pre-trained language models under the supervision of limited personality labels. This leads to inferior quality of post features and consequently affects the performance. In addition, they treat personality traits as one-hot classification labels, overlooking the semantic information within them. In this paper, we propose a large language model (LLM) based text augmentation enhanced personality detection model, which distills the LLM's knowledge to enhance the small model for personality detection, even when the LLM fails in this task. Specifically, we enable LLM to generate post analyses (augmentations) from the aspects of semantic, sentiment, and linguistic, which are critical for personality detection. By using contrastive learning to pull them together in the embedding space, the post encoder can better capture the psycho-linguistic information within the post representations, thus improving personality detection. Furthermore, we utilize the LLM to enrich the information of personality labels for enhancing the detection performance. Experimental results on the benchmark datasets demonstrate that our model outperforms the state-of-the-art methods on personality detection.

19 February 2024 in Information Sciences
Verified
Journal Article
Closed access
Linmei HuLinmei Hu
Linmei Hu
ZZZiwang Zhao
Ziwang Zhao
WQWeijian Qi
Weijian Qi
XSXuemeng Song
Xuemeng Song
LNLiqiang Nie
Liqiang Nie