1 code implementation • NeurIPS 2023 • Hanqi Yan, Lingjing Kong, Lin Gui, Yuejie Chi, Eric Xing, Yulan He, Kun Zhang
In this work, we tackle the domain-varying dependence between the content and the style variables inherent in the counterfactual generation task.
no code implementations • 23 Feb 2024 • Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He
This approach utilizes contrastive learning to align representations of in-context examples across different positions and introduces a consistency loss to ensure similar representations for inputs with different permutations.
no code implementations • 22 Feb 2024 • Hanqi Yan, Qinglin Zhu, Xinyu Wang, Lin Gui, Yulan He
While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources.
no code implementations • 1 Nov 2023 • Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He
Understanding in-context learning (ICL) capability that enables large language models (LLMs) to excel in proficiency through demonstration examples is of utmost importance.
no code implementations • 9 May 2023 • Hanqi Yan, Lin Gui, Menghan Wang, Kun Zhang, Yulan He
Explainable recommender systems can explain their recommendation decisions, enhancing user trust in the systems.
1 code implementation • 13 Feb 2023 • Hongjing Li, Hanqi Yan, Yanran Li, Li Qian, Yulan He, Lin Gui
When using prompt-based learning for text classification, the goal is to use a pre-trained language model (PLM) to predict a missing token in a pre-defined template given an input text, which can be mapped to a class label.
1 code implementation • 3 Jan 2023 • Runcong Zhao, Lin Gui, Hanqi Yan, Yulan He
Monitoring online customer reviews is important for business organisations to measure customer satisfaction and better manage their reputations.
1 code implementation • 24 Aug 2022 • Hanqi Yan, Lin Gui, Wenjie Li, Yulan He
In this paper, we propose to use the distribution of singular values of outputs of each transformer layer to characterise the phenomenon of token uniformity and empirically illustrate that a less skewed singular value distribution can alleviate the `token uniformity' problem.
1 code implementation • 20 Feb 2022 • Hanqi Yan, Lin Gui, Yulan He
Neural models developed in NLP however often compose word semantics in a hierarchical manner and text classification requires hierarchical modelling to aggregate local information in order to deal with topic and label shifts more effectively.
1 code implementation • ACL 2021 • Hanqi Yan, Lin Gui, Gabriele Pergola, Yulan He
To investigate the degree of reliance of existing ECE models on clause relative positions, we propose a novel strategy to generate adversarial examples in which the relative position information is no longer the indicative feature of cause clauses.
no code implementations • IJCNLP 2019 • Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu sun
The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks.