AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples

@inproceedings{Kang2018AdvEntuReAT,
  title={AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples},
  author={Dongyeop Kang and Tushar Khot and Ashish Sabharwal and E. Hovy},
  booktitle={ACL},
  year={2018}
}
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in entailment models via only a handful of rule templates. Second, to make the entailment model—a discriminator—more robust, we propose the first GAN-style approach for training it using a natural language example generator… Expand
Knowledge Enhanced Attention for Robust Natural Language Inference
TLDR
This paper applies the new attention to two popular types of NLI models: one is Transformer encoder, and the other is a decomposable model, and shows that the method can significantly improve their robustness. Expand
Generating Textual Adversarial Examples for Deep Learning Models: A Survey
TLDR
This article reviews research works that address this difference and generate textual adversarial examples on DNNs and collects, select, summarize, discuss and analyze these works in a comprehensive way and cover all the related information to make the article self-contained. Expand
Undersensitivity in Neural Reading Comprehension
TLDR
This work forms an adversarial attack which searches among semantic variations of the question for which a model erroneously predicts the same answer, and demonstrates that models trained on both SQuAD2.0 and NewsQA are vulnerable to this attack, and investigates data augmentation and adversarial training as defences. Expand
Translation-Based Matching Adversarial Network for Cross-Lingual Natural Language Inference
TLDR
An adversarial training framework to enhance both pre-trained models and classical neural models for cross-lingual natural language inference is proposed, which demonstrates that three popular neural models enhanced by the proposed framework significantly outperform the original models. Expand
Adversarial Attacks on Deep-learning Models in Natural Language Processing
TLDR
A systematic survey on preliminary knowledge of NLP and related seminal works in computer vision is presented, which collects all related academic works since the first appearance in 2017 and analyzes 40 representative works in a comprehensive way. Expand
Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
TLDR
Two probabilistic methods are proposed to build models that are more robust to hypothesis-only biases in Natural Language Inference datasets and transfer better than a baseline architecture in 9 out of 12 NLI datasets. Expand
Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models
TLDR
Quantitative evaluations with two state-of-the-art NLI baselines on SNLI and SciTail datasets in conjunction with ConceptNet and Aristo Tuple KGs show that BiCAM considerably improves the accuracy the incorporated NLI Baselines. Expand
Enhancing Natural Language Inference Using New and Expanded Training Data Sets and New Learning Models
TLDR
A modification to the “word-to-word” attention function which has been uniformly reused across several popular NLI architectures is proposed and the resulting models perform as well as their unmodified counterparts on the existing benchmarks and perform significantly well on the new benchmarks that emphasize “roles” and “entities”. Expand
Deep Adversarial Learning for NLP
TLDR
This tutorial provides a gentle introduction to the foundation of deep adversarial learning, as well as some practical problem formulations and solutions in NLP. Expand
Teaching Syntax by Adversarial Distraction
TLDR
Several datasets based on synthetic transformations of natural entailment examples in SNLI or FEVER are introduced, to teach aspects of grammar and word order. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Adversarial Example Generation with Syntactically Controlled Paraphrase Networks
TLDR
A combination of automated and human evaluations show that SCPNs generate paraphrases that follow their target specifications without decreasing paraphrase quality when compared to baseline (uncontrolled) paraphrase systems. Expand
Recognizing Textual Entailment via Multi-task Knowledge Assisted LSTM
TLDR
A deep neural network architecture called Multi-task Knowledge Assisted LSTM (MKAL) is proposed, which aims to conduct implicit inference with the assistant of KB and use predicate-to-predicate attention to detect the entailment between predicates. Expand
SciTaiL: A Textual Entailment Dataset from Science Question Answering
TLDR
A new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem, is presented, and it is demonstrated that one can improve accuracy on SCITAIL by 5% using a new neural model that exploits linguistic structure. Expand
CatGAN: Coupled Adversarial Transfer for Domain Generation
TLDR
A Coupled adversarial transfer GAN (CatGAN), an efficient solution to domain alignment and an effective alternative to conditional GAN without label constraint in generative learning is introduced. Expand
Annotation Artifacts in Natural Language Inference Data
TLDR
It is shown that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI, and that specific linguistic phenomena such as negation and vagueness are highly correlated with certain inference classes. Expand
A large annotated corpus for learning natural language inference
TLDR
The Stanford Natural Language Inference corpus is introduced, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning, which allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time. Expand
Triple Generative Adversarial Nets
TLDR
Triple-GAN as a unified model can simultaneously achieve the state-of-the-art classification results among deep generative models, and disentangle the classes and styles of the input and transfer smoothly in the data space via interpolation in the latent space class-conditionally. Expand
Adversarial Examples for Evaluating Reading Comprehension Systems
TLDR
This work proposes an adversarial evaluation scheme for the Stanford Question Answering Dataset that tests whether systems can answer questions about paragraphs that contain adversarially inserted sentences without changing the correct answer or misleading humans. Expand
Learned in Translation: Contextualized Word Vectors
TLDR
Adding context vectors to a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation to contextualize word vectors improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks. Expand
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
...
1
2
3
4
5
...