NLP AAAI

LAMPAT: Low-rank Adaption for Multilingual Paraphrasing using Adversarial Training

January 8, 2024

Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with low-resource languages, where data shortage is a significant problem. To generate a paraphrase in multilingual settings, previous studies have leveraged the knowledge from the machine translation field, i.e., forming a paraphrase through zero-shot machine translation in the same language. Despite good performance on human evaluation, those methods still require parallel translation datasets, thus making them inapplicable to languages that do not have parallel corpora. To mitigate that problem, we proposed the first unsupervised multilingual paraphrasing model, LAMPAT (Low-rank Adaptation for Multilingual Paraphrasing using Adversarial Training), by which monolingual dataset is sufficient enough to generate a human-like and diverse sentence. Throughout the experiments, we found out that our method not only works well for English but can generalize on unseen languages as well. Data and code are available at https://github.com/phkhanhtrinh23/LAMPAT.

Overall

< 1 minute

Le, Khoi M*; Pham, Trinh Khanh*; Quan, Tho; Luu, Anh Tuan

Share Article

Related publications

NLP NAACL Top Tier
April 4, 2024

*Thanh-Thien Le, *Viet Dao, *Linh Van Nguyen, Nhung Nguyen, Linh Ngo Van, Thien Huu Nguyen

GA-LLM NLP NAACL Top Tier
April 4, 2024

Thang Le, Tuan Luu

NLP EMNLP Findings
January 26, 2024

Thang Le, Luu Anh Tuan