Zhao Meng


2022

pdf bib
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks
Zhao Meng | Yihan Dong | Mrinmaya Sachan | Roger Wattenhofer
Findings of the Association for Computational Linguistics: NAACL 2022

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning. We create a word-level adversarial attack generating hard positives on-the-fly as adversarial examples during contrastive learning. In contrast to previous works, our method improves model robustness without using any labeled data. Experimental results show that our method improves robustness of BERT against four different word substitution-based adversarial attacks, and combining our method with adversarial training gives higher robustness than adversarial training alone. As our method improves the robustness of BERT purely with unlabeled data, it opens up the possibility of using large text datasets to train robust language models against word substitution-based adversarial attacks.

pdf bib
TempCaps: A Capsule Network-based Embedding Model for Temporal Knowledge Graph Completion
Guirong Fu | Zhao Meng | Zhen Han | Zifeng Ding | Yunpu Ma | Matthias Schubert | Volker Tresp | Roger Wattenhofer
Proceedings of the Sixth Workshop on Structured Prediction for NLP

Temporal knowledge graphs store the dynamics of entities and relations during a time period. However, typical temporal knowledge graphs often suffer from incomplete dynamics with missing facts in real-world scenarios. Hence, modeling temporal knowledge graphs to complete the missing facts is important. In this paper, we tackle the temporal knowledge graph completion task by proposing TempCaps, which is a Capsule network-based embedding model for Temporal knowledge graph completion. TempCaps models temporal knowledge graphs by introducing a novel dynamic routing aggregator inspired by Capsule Networks. Specifically, TempCaps builds entity embeddings by dynamically routing retrieved temporal relation and neighbor information. Experimental results demonstrate that TempCaps reaches state-of-the-art performance for temporal knowledge graph completion. Additional analysis also shows that TempCaps is efficient.

2021

pdf bib
KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
Yiran Xing | Zai Shi | Zhao Meng | Gerhard Lakemeyer | Yunpu Ma | Roger Wattenhofer
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART architecture (Lewis et al., 2020) to a multimodal model with visual and textual inputs. We further develop novel pretraining tasks to improve the model performance on the Visual Commonsense Generation (VCG) task. In particular, our pretraining task of Knowledge-based Commonsense Generation (KCG) boosts model performance on the VCG task by leveraging commonsense knowledge from a large language model pretrained on external commonsense knowledge graphs. To the best of our knowledge, we are the first to propose a dedicated task for improving model performance on the VCG task. Experimental results show that our model reaches state-of-the-art performance on the VCG task (Park et al., 2020) by applying these novel pretraining tasks.

2020

pdf bib
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples
Zhao Meng | Roger Wattenhofer
Proceedings of the 28th International Conference on Computational Linguistics

Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generating natural language adversarial examples. Our attack generates adversarial examples by iteratively approximating the decision boundary of Deep Neural Networks (DNNs). Experiments on two datasets with two different models show that our attack fools natural language models with high success rates, while only replacing a few words. Human evaluation shows that adversarial examples generated by our attack are hard for humans to recognize. Further experiments show that adversarial training can improve model robustness against our attack.

2018

pdf bib
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
Zhao Meng | Lili Mou | Zhi Jin
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2016

pdf bib
How Transferable are Neural Networks in NLP Applications?
Lili Mou | Zhao Meng | Rui Yan | Ge Li | Yan Xu | Lu Zhang | Zhi Jin
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing