Zhiyuan Zhang


2021

pdf bib
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Wenkai Yang | Lei Li | Zhiyuan Zhang | Xuancheng Ren | Xu Sun | Bin He
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/lancopku/Embedding-Poisoning.

pdf bib
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects
Zhiyuan Zhang | Xuancheng Ren | Qi Su | Xu Sun | Bin He
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Side effects during neural network tuning are typically measured by overall accuracy changes. However, we find that even with similar overall accuracy, existing tuning methods result in non-negligible instance-wise side effects. Motivated by neuroscientific evidence and theoretical results, we demonstrate that side effects can be controlled by the number of changed parameters and thus, we propose to conduct neural network surgery by only modifying a limited number of parameters. Neural network surgery can be realized using diverse techniques and we investigate three lines of methods. Experimental results on representative tuning problems validate the effectiveness of the surgery approach. The dynamic selecting method achieves the best overall performance that not only satisfies the tuning goal but also induces fewer instance-wise side effects by changing only 10-5 of the parameters.

pdf bib
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
Runxin Xu | Fuli Luo | Zhiyuan Zhang | Chuanqi Tan | Baobao Chang | Songfang Huang | Fei Huang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent pretrained language models extend from millions to billions of parameters. Thus the need to fine-tune an extremely large pretrained model with a limited training corpus arises in various downstream tasks. In this paper, we propose a straightforward yet effective fine-tuning technique, Child-Tuning, which updates a subset of parameters (called child network) of large pretrained models via strategically masking out the gradients of the non-child network during the backward process. Experiments on various downstream tasks in GLUE benchmark show that Child-Tuning consistently outperforms the vanilla fine-tuning by 1.5 8.6 average score among four different pretrained models, and surpasses the prior fine-tuning techniques by 0.6 1.3 points. Furthermore, empirical results on domain transfer and task transfer show that Child-Tuning can obtain better generalization performance by large margins.

2020

pdf bib
Rethinking Skip Connection with Layer Normalization
Fenglin Liu | Xuancheng Ren | Zhiyuan Zhang | Xu Sun | Yuexian Zou
Proceedings of the 28th International Conference on Computational Linguistics

Skip connection is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could by addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection. Inspired by the findings, we further propose to adaptively adjust the scale of the input by recursively applying skip connection with layer normalization, which promotes the performance substantially and generalizes well across diverse tasks including both machine translation and image classification datasets.

pdf bib
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models
Zhiyuan Zhang | Xiaoqian Liu | Yi Zhang | Qi Su | Xu Sun | Bin He
Findings of the Association for Computational Linguistics: EMNLP 2020

Conventional knowledge graph embedding (KGE) often suffers from limited knowledge representation, leading to performance degradation especially on the low-resource problem. To remedy this, we propose to enrich knowledge representation via pretrained language models by leveraging world knowledge from pretrained models. Specifically, we present a universal training framework named Pretrain-KGE consisting of three phases: semantic-based fine-tuning phase, knowledge extracting phase and KGE training phase. Extensive experiments show that our proposed Pretrain-KGE can improve results over KGE models, especially on solving the low-resource problem.

2018

pdf bib
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text
Xuancheng Ren | Xu Sun | Ji Wen | Bingzhen Wei | Weidong Zhan | Zhiyuan Zhang
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)