arXiv subjects

Zhengyan Zhang

Publications and source records attributed to Zhengyan Zhang.

48 records · Page 3Linked to original sources

arXiv2021

Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding textual adversarial examples during training. However, the number of adversarial examples for text augmentation is still extremely insufficient due to the exponentially large attack search space. In this work, we propose a simple and effective method to cover a much larger proportion of the attack search space, called Adversarial and Mixup Data Augmentation (AMDA). Specifically, AMDA linearly interpolates the representations of pairs of training samples to form new virtual samples, which are more abundant and diverse than the discrete text adversarial examples in conventional ADA. Moreover, to fairly evaluate the robustness of different models, we adopt a challenging evaluation setup, which generates a new set of adversarial examples targeting each model. In text classification experiments of BERT and RoBERTa, AMDA achieves significant robustness gains under two strong adversarial attacks and alleviates the performance degradation of ADA on the clean data. Our code is available at: https://github.com/thunlp/MixADA .

cs.CL↗

arXiv2021

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned triggers but behave properly on normal inputs during inference. As a sort of emergent attack, backdoor attacks in natural language processing (NLP) are investigated insufficiently. As far as we know, almost all existing textual backdoor attack methods insert additional contents into normal samples as triggers, which causes the trigger-embedded samples to be detected and the backdoor attacks to be blocked without much effort. In this paper, we propose to use the syntactic structure as the trigger in textual backdoor attacks. We conduct extensive experiments to demonstrate that the syntactic trigger-based attack method can achieve comparable attack performance (almost 100% success rate) to the insertion-based methods but possesses much higher invisibility and stronger resistance to defenses. These results also reveal the significant insidiousness and harmfulness of textual backdoor attacks. All the code and data of this paper can be obtained at https://github.com/thunlp/HiddenKiller.

cs.CL↗

arXiv2021

CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models

Fine-tuning pre-trained language models (PLMs) has demonstrated its effectiveness on various downstream NLP tasks recently. However, in many low-resource scenarios, the conventional fine-tuning strategies cannot sufficiently capture the important semantic features for downstream tasks. To address this issue, we introduce a novel framework (named "CSS-LM") to improve the fine-tuning phase of PLMs via contrastive semi-supervised learning. Specifically, given a specific task, we retrieve positive and negative instances from large-scale unlabeled corpora according to their domain-level and class-level semantic relatedness to the task. We then perform contrastive semi-supervised learning on both the retrieved unlabeled and original labeled instances to help PLMs capture crucial task-related semantic features. The experimental results show that CSS-LM achieves better results than the conventional fine-tuning strategy on a series of downstream tasks with few-shot settings, and outperforms the latest supervised contrastive fine-tuning strategies. Our datasets and source code will be available to provide more details.

cs.CL↗

arXiv2021

Quincke oscillations of colloids at planar electrodes

Dielectric particles in weakly conducting fluids rotate spontaneously when subject to strong electric fields. Such Quincke rotation near a plane electrode leads to particle translation that enables physical models of active matter. Here, we show that Quincke rollers can also exhibit oscillatory dynamics, whereby particles move back and forth about a fixed location. We explain how oscillations arise for micron-scale particles commensurate with the thickness of a field-induced boundary layer in the nonpolar electrolyte. This work enables the design of colloidal oscillators.

cond-mat.soft↗

arXiv2020

Adversarial Language Games for Advanced Natural Language Intelligence

We study the problem of adversarial language games, in which multiple agents with conflicting goals compete with each other via natural language interactions. While adversarial language games are ubiquitous in human activities, little attention has been devoted to this field in natural language processing. In this work, we propose a challenging adversarial language game called Adversarial Taboo as an example, in which an attacker and a defender compete around a target word. The attacker is tasked with inducing the defender to utter the target word invisible to the defender, while the defender is tasked with detecting the target word before being induced by the attacker. In Adversarial Taboo, a successful attacker must hide its intention and subtly induce the defender, while a competitive defender must be cautious with its utterances and infer the intention of the attacker. Such language abilities can facilitate many important downstream NLP tasks. To instantiate the game, we create a game environment and a competition platform. Comprehensive experiments and empirical studies on several baseline attack and defense strategies show promising and interesting results. Based on the analysis on the game and experiments, we discuss multiple promising directions for future research.

cs.CL↗

arXiv2020

CPM: A Large-scale Generative Chinese Pre-trained Language Model

Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot) learning. However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available. In this technical report, we release the Chinese Pre-trained Language Model (CPM) with generative pre-training on large-scale Chinese training data. To the best of our knowledge, CPM, with 2.6 billion parameters and 100GB Chinese training data, is the largest Chinese pre-trained language model, which could facilitate several downstream Chinese NLP tasks, such as conversation, essay generation, cloze test, and language understanding. Extensive experiments demonstrate that CPM achieves strong performance on many NLP tasks in the settings of few-shot (even zero-shot) learning. The code and parameters are available at https://github.com/TsinghuaAI/CPM-Generate.

cs.CL↗

arXiv2020

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER, we encode textual entity descriptions with a PLM as their embeddings, and then jointly optimize the KE and language modeling objectives. Experimental results show that KEPLER achieves state-of-the-art performances on various NLP tasks, and also works remarkably well as an inductive KE model on KG link prediction. Furthermore, for pre-training and evaluating KEPLER, we construct Wikidata5M, a large-scale KG dataset with aligned entity descriptions, and benchmark state-of-the-art KE methods on it. It shall serve as a new KE benchmark and facilitate the research on large KG, inductive KE, and KG with text. The source code can be obtained from https://github.com/THU-KEG/KEPLER.

cs.CL↗

arXiv2020

Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually overparameterized and significantly increase the computational overhead in applications. It is intuitive to address this issue by model compression. In this work, we propose a method, called Single-Shot Meta-Pruning, to compress deep pre-trained Transformers before fine-tuning. Specifically, we focus on pruning unnecessary attention heads adaptively for different downstream tasks. To measure the informativeness of attention heads, we train our Single-Shot Meta-Pruner (SMP) with a meta-learning paradigm aiming to maintain the distribution of text representations after pruning. Compared with existing compression methods for pre-trained models, our method can reduce the overhead of both fine-tuning and inference. Experimental results show that our pruner can selectively prune 50% of attention heads with little impact on the performance on downstream tasks and even provide better text representations. The source code will be released in the future.

cs.CL↗

arXiv2020

Train No Evil: Selective Masking for Task-Guided Pre-Training

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the fine-tuning stage usually suffers from insufficient supervised data, the models cannot always well capture the domain-specific and task-specific patterns. In this paper, we propose a three-stage framework by adding a task-guided pre-training stage with selective masking between general pre-training and fine-tuning. In this stage, the model is trained by masked language modeling on in-domain unsupervised data to learn domain-specific patterns and we propose a novel selective masking strategy to learn task-specific patterns. Specifically, we design a method to measure the importance of each token in sequences and selectively mask the important tokens. Experimental results on two sentiment analysis tasks show that our method can achieve comparable or even better performance with less than 50% of computation cost, which indicates our method is both effective and efficient. The source code of this paper can be obtained from https://github.com/thunlp/SelectiveMasking.

cs.CL↗

arXiv2019

ERNIE: Enhanced Language Representation with Informative Entities

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The source code of this paper can be obtained from https://github.com/thunlp/ERNIE.

cs.CL↗

arXiv2018

COSINE: Compressive Network Embedding on Large-scale Information Networks

There is recently a surge in approaches that learn low-dimensional embeddings of nodes in networks. As there are many large-scale real-world networks, it's inefficient for existing approaches to store amounts of parameters in memory and update them edge after edge. With the knowledge that nodes having similar neighborhood will be close to each other in embedding space, we propose COSINE (COmpresSIve NE) algorithm which reduces the memory footprint and accelerates the training process by parameters sharing among similar nodes. COSINE applies graph partitioning algorithms to networks and builds parameter sharing dependency of nodes based on the result of partitioning. With parameters sharing among similar nodes, COSINE injects prior knowledge about higher structural information into training process which makes network embedding more efficient and effective. COSINE can be applied to any embedding lookup method and learn high-quality embeddings with limited memory and shorter training time. We conduct experiments of multi-label classification and link prediction, where baselines and our model have the same memory usage. Experimental results show that COSINE gives baselines up to 23% increase on classification and up to 25% increase on link prediction. Moreover, time of all representation learning methods using COSINE decreases from 30% to 70%.

cs.SI↗

arXiv2018

A Unified Framework for Community Detection and Network Representation Learning

Network representation learning (NRL) aims to learn low-dimensional vectors for vertices in a network. Most existing NRL methods focus on learning representations from local context of vertices (such as their neighbors). Nevertheless, vertices in many complex networks also exhibit significant global patterns widely known as communities. It's intuitive that vertices in the same community tend to connect densely and share common attributes. These patterns are expected to improve NRL and benefit relevant evaluation tasks, such as link prediction and vertex classification. Inspired by the analogy between network representation learning and text modeling, we propose a unified NRL framework by introducing community information of vertices, named as Community-enhanced Network Representation Learning (CNRL). CNRL simultaneously detects community distribution of each vertex and learns embeddings of both vertices and communities. Moreover, the proposed community enhancement mechanism can be applied to various existing NRL models. In experiments, we evaluate our model on vertex classification, link prediction, and community detection using several real-world datasets. The results demonstrate that CNRL significantly and consistently outperforms other state-of-the-art methods while verifying our assumptions on the correlations between vertices and communities.

cs.SI↗