Challenge: Existing domain adaptation techniques for question deduplication and RTE focus on transferring category independent knowledge between domains.
Approach: They propose to use gradient reversal to explicitly learn shared and unshared (domain specific) representations between two textual domains to compensate for domain mismatch while distilling domain specific knowledge.
Outcome: The proposed approach outperforms other methods on question deduplication and on recognizing textual entailment tasks, while still distilling domain specific knowledge.

Similar Papers

Adversarial Domain Adaptation for Duplicate Question Detection (D18-1)

Copied to clipboard

Challenge: Recent years have seen the rise of community question answering forums . duplicate questions easily become ubiquitous as users often ask the same question, possibly in a slightly different formulation, making it difficult to find the best (or one correct) answer.
Approach: They propose to use domain adaptation to detect duplicate questions in forums . they find that domain adaptation improves performance over multiple pairs of domains .
Outcome: The proposed approach improves 5.6% over the best baseline across multiple pairs of domains.
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.
Gradient-based Adversarial Attacks against Text Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for obtaining adversarial examples are difficult with text data.
Approach: They propose a gradient-based adversarial attack against transformer models that searches for a distribution of adversarials parameterized by a continuous-valued matrix.
Outcome: The proposed attack outperforms existing methods on a variety of natural language tasks with matching imperceptibility.
Improving Domain Adaptation Translation with Domain Invariant and Specific Information (N19-1)

Copied to clipboard

Challenge: Neural machine translation models are based on the encoder-decoder architecture, which makes them overfitting to frequent observations.
Approach: They propose a method to explicitly model out-of-domain information in an encoder-decoder framework . they propose combining out- of-domain training data with out-out-of domain data .
Outcome: The proposed method outperforms baselines on multiple data sets.
Domain Adversarial Fine-Tuning as an Effective Regularizer (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing fine-tuning techniques can degrade general-domain representations . however, fine-timing can lead to catastrophic forgetting of knowledge .
Approach: They propose a new regularization technique that complements the task-specific loss used during fine-tuning with an adversarial objective.
Outcome: Empirical results show that AFTER improves performance on various natural language understanding tasks compared to standard fine-tuning.
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.
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.
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.
Domain-agnostic Question-Answering with Adversarial Training (D19-58)

Copied to clipboard

Challenge: Adapting models to new domain without finetuning is a challenging problem in deep learning.
Approach: They propose an adversarial training framework for domain generalization in Question Answering task using a conventional QA model and a discriminator.
Outcome: The proposed model outperforms the baseline model on Question Answering (QA) task.
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for adversarial samples are poorly applied in computer vision . however, textual adversarials are still vulnerable to small perturbations .
Approach: They propose a framework to extend existing adversarial attack methods to textual adversarials by adding optimized perturbations to embedding layer and amplifying them in forward propagation process.
Outcome: The proposed framework achieves better performance even using proxy gradient information and produces more fluent and grammatical adversarial samples compared to baseline methods.

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