31 citations · 116 across the 14 of their papers we have counts for
13 papers · 1 filter
Watermarking Pre-trained Language Models with Backdooring
Chenxi Gu, Chengsong Huang, Xiaoqing Zheng +2
Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific…
Improving the Adversarial Robustness of NLP Models by Information Bottleneck
Cenyuan Zhang, Xiang Zhou, Yixin Wan +3
Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manip…
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution
Zongyi Li, Jianhan Xu, Jiehang Zeng +5
Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversari…
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
Chong Li, Cenyuan Zhang, Xiaoqing Zheng +1
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spe…
Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
Jiehang Zeng, Xiaoqing Zheng, Jianhan Xu +3
Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing ce…
Alleviate Exposure Bias in Sequence Prediction \\ with Recurrent Neural Networks
Liping Yuan, Jiangtao Feng, Xiaoqing Zheng +1
A popular strategy to train recurrent neural networks (RNNs), known as ``teacher forcing'' takes the ground truth as input at each time step and makes the later predictions partly…
Unsupervised Word Segmentation with Bi-directional Neural Language Model
Lihao Wang, Zongyi Li, Xiaoqing Zheng
We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Suc…
SparseGAN: Sparse Generative Adversarial Network for Text Generation
Liping Yuan, Jiehang Zeng, Xiaoqing Zheng
It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differ…
Unsupervised Summarization by Jointly Extracting Sentences and Keywords
Zongyi Li, Xiaoqing Zheng, Jun He
We present RepRank, an unsupervised graph-based ranking model for extractive multi-document summarization in which the similarity between words, sentences, and word-to-sentence can…
Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference
Lu Liu, Zhenqiao Song, Xiaoqing Zheng +1
One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs. However, coreferent m…
Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
Yi Zhou, Xiaoqing Zheng, Cho-Jui Hsieh +2
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples. In this paper, we propose…
Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework
Jiehang Zeng, Lu Liu, Xiaoqing Zheng
Many large-scale knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and de…
Chinese Named Entity Recognition Augmented with Lexicon Memory
Yi Zhou, Xiaoqing Zheng, Xuanjing Huang
Inspired by a concept of content-addressable retrieval from cognitive science, we propose a novel fragment-based model augmented with a lexicon-based memory for Chinese NER, in whi…