Guang Liu


pdf bib
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup
Guang Liu | Yuzhao Mao | Huang Hailong | Gao Weiguo | Li Xuan
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Mixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes locally linear constraints on the model’s input space. However, such strict linear constraints often lead to under-fitting which degrades the effects of regularization. Noticeably, this issue is getting more serious when the resource is extremely limited. To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a “min-max-rand” formulation, to relax the Locally Linear Constraints in Mixup. Specifically, AMP adds a small adversarial perturbation to the mixing coefficients rather than the examples. Thus, slight non-linearity is injected in-between the synthetic examples and synthetic labels. By training on these data, the deep networks are further regularized, and thus achieve a lower predictive error rate. Experiments on five text classification benchmarks and five backbone models have empirically shown that our methods reduce the error rate over Mixup variants in a significant margin (up to 31.3%), especially in low-resource conditions (up to 17.5%).

pdf bib
DialogueTRM: Exploring Multi-Modal Emotional Dynamics in a Conversation
Yuzhao Mao | Guang Liu | Xiaojie Wang | Weiguo Gao | Xuan Li
Findings of the Association for Computational Linguistics: EMNLP 2021

Emotion dynamics formulates principles explaining the emotional fluctuation during conversations. Recent studies explore the emotion dynamics from the self and inter-personal dependencies, however, ignoring the temporal and spatial dependencies in the situation of multi-modal conversations. To address the issue, we extend the concept of emotion dynamics to multi-modal settings and propose a Dialogue Transformer for simultaneously modeling the intra-modal and inter-modal emotion dynamics. Specifically, the intra-modal emotion dynamics is to not only capture the temporal dependency but also satisfy the context preference in every single modality. The inter-modal emotional dynamics aims at handling multi-grained spatial dependency across all modalities. Our models outperform the state-of-the-art with a margin of 4%-16% for most of the metrics on three benchmark datasets.


pdf bib
Attribute based Chinese Named Entity Recognition and Disambiguation
Wei Han | Guang Liu | Yuzhao Mao | Zhenni Huang
Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing