Yixuan Huo

Mitigating systematic bias in polymer Tg prediction via role-decoupled graph readout

Wanyi Chen, Zhanjie Liu, Yixuan Huo, Jun Liu et autres

cn (code pays fourni par la source)

Hierarchical Aware Relation Extraction Based on Prompt-Tuning

Xin Wen, Yixuan Huo, Jinqiao Shi, Majing Su et autres

Recently, the prompt-tuning based method has made great progress in natural language processing tasks, where the input sentence is warped into a natural language template and then the sentence classification task is covered by a masked language modeling task. To make predictions, …

cn (code pays fourni par la source)

Document-Level Relation Extraction from Macro-Micro Perspective

Xin Wen, Yixuan Huo, Jinqiao Shi, Majing Su et autres

As an important task in natural language processing, relation extraction (RE) plays an important role in information extraction and knowledge base construction. Previous studies have primarily focused on relation classification at the single-sentence level, which limits the ability to capture inter-sentential dependencies …

cn (code pays fourni par la source)

Decode the Dark Side of the Language: Applications of LLMs in the Dark Web

Hongfan Chen, Yigang Diao, Hui Xiang, Yixuan Huo et autres

Previous studies have discovered that Transformers pre-trained on large scale datasets have a great advantage over traditional methods and can achieve human-level performance in many NLP tasks. Various encoder-only models like BERT and RoBERTa are used in the researches of the language …

cn (code pays fourni par la source)

URM4DMU: An User Representation Model for Darknet Markets Users

Hongmeng Liu, Jiapeng Zhao, Yixuan Huo, Yuyan Wang et autres

Darknet markets provide a large platform for trading illicit goods and services due to their anonymity. Learning an invariant representation of each user based on their posts on different markets makes it easy to aggregate user information across different platforms, which helps …

cn (code pays fourni par la source)

URM4DMU: an user represention model for darknet markets users

Hongmeng Liu, Jiapeng Zhao, Yixuan Huo, Yuyan Wang et autres

Darknet markets provide a large platform for trading illicit goods and services due to their anonymity. Learning an invariant representation of each user based on their posts on different markets makes it easy to aggregate user information across different platforms, which helps …