Challenge: Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation.
Approach: They propose a method that introduces multiple points of confusion within the context and shows dependence on insertion location of the distractor.
Outcome: The proposed methods improve robustness against adversarial evaluation but weak generalization to the source domain and new domains and languages.

Similar Papers

Impact of Adversarial Training on Robustness and Generalizability of Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Adversarial training is widely acknowledged as the most effective defense against adversarial attacks, but achieving both robustness and generalization requires a trade-off.
Approach: They propose to compare pre-training data augmentation and training time input perturbations with embedding space perturbations to find out whether they improve generalization.
Outcome: The proposed methods improve generalization and robustness of the trained models.
Data Augmentation with Adversarial Training for Cross-Lingual NLI (2021.acl-long)

Copied to clipboard

Challenge: Existing approaches to train cross-lingual models with labeled data are subpar, resulting in subpar results.
Approach: They propose a data augmentation strategy that enriches data to reflect more diversity in a semantically faithful way and leverages adversarial training regimens to achieve greater robustness.
Outcome: The proposed approach improves cross-lingual inference by leveraging the data to reflect more diversity in a semantically faithful way.
Robust Semantic Parsing with Adversarial Learning for Domain Generalization (N19-2)

Copied to clipboard

Challenge: Using adversarial learning to train models on a higher level of abstraction to increase their robustness to lexical and stylistic variations is crucial for the integration of Semantic Parsing technologies in real applications.
Approach: They propose to perform Semantic Parsing with a domain classification adversarial task and an unsupervised domain discovery approach that yields equivalent improvements.
Outcome: The proposed approach improves on a French corpus of encyclopedic documents annotated with FrameNet and an unsupervised domain discovery approach yields equivalent improvements.
Manifold Adversarial Augmentation for Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Challenge: Recent studies show that NMT models can drop significantly when small perturbations are added to input sentences.
Approach: They propose a data augmentation approach to sample sentences from the vicinity distributions in higher-level representations.
Outcome: The proposed method improves translation accuracy on training samples from higher-level representations.
Robust Machine Comprehension Models via Adversarial Training (N18-2)

Copied to clipboard

Challenge: Existing models for the Stanford Question Answering Dataset suffer from a 50% decrease in F1 score during adversarial evaluation based on AddSent.
Approach: They propose an alternative adversary-generation algorithm, AddSentDiverse, that significantly increases the variance within the adversarial training data by providing effective examples that punish the model for making certain superficial assumptions.
Outcome: The proposed algorithm can achieve a 36.5% increase in F1 score while maintaining performance on the regular SQuAD task.
Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models (2021.acl-short)

Copied to clipboard

Challenge: Pre-trained language models have achieved human-level performance on many Machine Reading Comprehension (MRC) tasks, but it remains unclear whether these models truly understand language or answer questions by exploiting statistical biases in datasets.
Approach: They propose a method to attack MRC models by exposing statistical biases in a RACE dataset and propose an augmented training method that can greatly reduce models’ statistical bias.
Outcome: The proposed method can reduce models’ statistical biases from human-level performance to chance-level.
What’s in a Domain? Learning Domain-Robust Text Representations using Adversarial Training (N18-2)

Copied to clipboard

Challenge: a key roadblock is application to new domains, unseen in training.
Approach: They propose a method to optimise in- and out-of-domain accuracy by combing domain-specific and domain-general components with adversarial training for domain.
Outcome: The proposed method improves on domain adaptation and domain-adversarial training.
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder (2021.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that models can be easily fooled by intentionally designed adversarial examples.
Approach: They propose two efficient approaches for generating adversarial perturbations on embeddings and propose two new approaches to help model learn adversarials more efficiently.
Outcome: The proposed approaches outperform strong baselines on various text classification datasets and the model's performance drops less under adversarial attack.
Adversarial Domain Adaptation for Machine Reading Comprehension (D19-1)

Copied to clipboard

Challenge: Existing models for machine reading comprehension rely on large amounts of human-annotated in-domain data.
Approach: They propose an unsupervised domain adaptation framework for Machine Reading Comprehension where the source domain has a large amount of labeled data, while only unlabeled passages are available in the target domain.
Outcome: The proposed framework can be generalizable to different MRC models and datasets and can be extended to semi-supervised learning.
Adversarial Domain Adaptation Using Artificial Titles for Abstractive Title Generation (P19-1)

Copied to clipboard

Challenge: Obtaining good quality labeled data can be difficult and expensive for abstractive summarization models . authors propose the use of artificial titles for unlabeled target documents .
Approach: They propose to use artificial titles and sequential training to capture grammatical style of unlabeled target domains to adapt to/from news articles and Stack Exchange posts.
Outcome: The proposed techniques can boost performance for unsupervised adaptation and fine-tuning with limited target data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations