Papers with synonym substitution
PromptDA: Label-guided Data Augmentation for Prompt-based Few Shot Learners (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on prompt-based few-shot tuning focus on deriving proper label words with a verbalizer or generating prompt templates to elicit semantics from PLMs. |
| Approach: | They propose a framework that leverages label semantics for prompt-based tuning. |
| Outcome: | The proposed framework improves on few-shot text classification tasks by leveraging label semantics and data augmentation. |
Certified Robustness to Programmable Transformations in LSTMs (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing techniques for certifying robustness of LSTMs and extensions of lsts are prone to adversarial examples. |
| Approach: | They propose an approach to certify robustness of LSTMs and extensions of lstms . they show that their approach can train models more robust to combinations of string transformations - a key advantage of existing certification approaches . |
| Outcome: | The proposed approach can show high certification accuracy of the resulting models. |
Boosting Text Augmentation via Hybrid Instance Filtering Framework (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing text augmentation methods generate instances with shifted feature spaces, which leads to a drop in performance on large datasets. |
| Approach: | They propose a hybrid instance-filtering framework that generates instances with shifted feature spaces, which leads to a drop in performance on augmented data. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three classification tasks and nine public datasets. |
Neural Linguistic Steganography (D19-1)
Copied to clipboard
| Challenge: | linguistic steganography encrypts a secret message into a cover signal . language is a pragmatic cover signal due to its benign occurrence and independence from any one medium. |
| Approach: | They propose a technique that encrypts a secret message into a cover signal . language is a particularly pragmatic cover signal due to its benign occurrence . |
| Outcome: | The proposed technique generates realistic looking cover sentences as evaluated by humans while preserving security by matching the cover message distribution with the language model distribution. |
Towards Robustness of Text-to-SQL Models against Synonym Substitution (2021.acl-long)
Copied to clipboard
Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R. Woodward, Jinxia Xie, Pengsheng Huang
| Challenge: | Existing text-to-SQL models rely on lexical matching between words in NL questions and tokens in table schemas, which may break the schema linking mechanism. |
| Approach: | They propose a human-curated dataset for text-to-SQL translation . they replace schema-related words with manually selected synonyms . |
| Outcome: | The proposed model outperforms its counterparts without the defense. |
CERT-ED: Certifiably Robust Text Classification for Edit Distance (2024.findings-emnlp)
Copied to clipboard
| Challenge: | randomized smoothing has emerged as promising approach for certifying robustness to adversarial examples. |
| Approach: | They propose a method for certifying robustness to adversarial examples . they adapt Randomized Deletion and propose CERTified Edit Distance defense . |
| Outcome: | The proposed method outperforms existing methods in 4 out of 5 datasets in accuracy and cardinality. |