InfoBERT: Improving Robustness of Language Models from An Information
Theoretic Perspective
- URL: http://arxiv.org/abs/2010.02329v4
- Date: Mon, 22 Mar 2021 11:44:30 GMT
- Title: InfoBERT: Improving Robustness of Language Models from An Information
Theoretic Perspective
- Authors: Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li,
Jingjing Liu
- Abstract summary: Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks.
Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks.
We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
- Score: 84.78604733927887
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large-scale language models such as BERT have achieved state-of-the-art
performance across a wide range of NLP tasks. Recent studies, however, show
that such BERT-based models are vulnerable facing the threats of textual
adversarial attacks. We aim to address this problem from an
information-theoretic perspective, and propose InfoBERT, a novel learning
framework for robust fine-tuning of pre-trained language models. InfoBERT
contains two mutual-information-based regularizers for model training: (i) an
Information Bottleneck regularizer, which suppresses noisy mutual information
between the input and the feature representation; and (ii) a Robust Feature
regularizer, which increases the mutual information between local robust
features and global features. We provide a principled way to theoretically
analyze and improve the robustness of representation learning for language
models in both standard and adversarial training. Extensive experiments
demonstrate that InfoBERT achieves state-of-the-art robust accuracy over
several adversarial datasets on Natural Language Inference (NLI) and Question
Answering (QA) tasks. Our code is available at
https://github.com/AI-secure/InfoBERT.
Related papers
- Cross-Lingual NER for Financial Transaction Data in Low-Resource
Languages [70.25418443146435]
We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data.
We employ two independent datasets of SMSs in English and Arabic, each carrying semi-structured banking transaction information.
With access to only 30 labeled samples, our model can generalize the recognition of merchants, amounts, and other fields from English to Arabic.
arXiv Detail & Related papers (2023-07-16T00:45:42Z) - Large Language Models with Controllable Working Memory [64.71038763708161]
Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP)
What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining.
How the model's world knowledge interacts with the factual information presented in the context remains under explored.
arXiv Detail & Related papers (2022-11-09T18:58:29Z) - TunBERT: Pretrained Contextualized Text Representation for Tunisian
Dialect [0.0]
We investigate the feasibility of training monolingual Transformer-based language models for under represented languages.
We show that the use of noisy web crawled data instead of structured data is more convenient for such non-standardized language.
Our best performing TunBERT model reaches or improves the state-of-the-art in all three downstream tasks.
arXiv Detail & Related papers (2021-11-25T15:49:50Z) - Interpreting Language Models Through Knowledge Graph Extraction [42.97929497661778]
We compare BERT-based language models through snapshots of acquired knowledge at sequential stages of the training process.
We present a methodology to unveil a knowledge acquisition timeline by generating knowledge graph extracts from cloze "fill-in-the-blank" statements.
We extend this analysis to a comparison of pretrained variations of BERT models (DistilBERT, BERT-base, RoBERTa)
arXiv Detail & Related papers (2021-11-16T15:18:01Z) - Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of
Language Models [86.02610674750345]
Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations.
All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
arXiv Detail & Related papers (2021-11-04T12:59:55Z) - Leveraging Advantages of Interactive and Non-Interactive Models for
Vector-Based Cross-Lingual Information Retrieval [12.514666775853598]
We propose a novel framework to leverage the advantages of interactive and non-interactive models.
We introduce semi-interactive mechanism, which builds our model upon non-interactive architecture but encodes each document together with its associated multilingual queries.
Our methods significantly boost the retrieval accuracy while maintaining the computational efficiency.
arXiv Detail & Related papers (2021-11-03T03:03:19Z) - Neural Models for Offensive Language Detection [0.0]
Offensive language detection is an ever-growing natural language processing (NLP) application.
We believe contributing to improving and comparing different machine learning models to fight such harmful contents is an important and challenging goal for this thesis.
arXiv Detail & Related papers (2021-05-30T13:02:45Z) - Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting.
Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking.
We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
arXiv Detail & Related papers (2020-10-24T11:55:28Z) - Coreferential Reasoning Learning for Language Representation [88.14248323659267]
We present CorefBERT, a novel language representation model that can capture the coreferential relations in context.
The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks.
arXiv Detail & Related papers (2020-04-15T03:57:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.