LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training
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 ($\textbf{L}$ow-rank $\textbf{A}$daptation for $\textbf{M}$ultilingual $\textbf{P}$araphrasing using $\textbf{A}$dversarial $\textbf{T}$raining), 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/VinAIResearch/LAMPAT.
Code (1)
Tasks
Multilingual Paraphrase GenerationSentenceSimilar Papers 제목 키워드 기반
Russian Paraphrasers: Paraphrase with Transformers
This paper studies the generation methods for paraphrasing in the Russian language. There are several transformer-based models (Russian and multilingual) trained on a collected corpus of paraphrases. We compare different…
CODA: Counting Objects via Scale-aware Adversarial Density Adaption
Recent advances in crowd counting have achieved promising results with increasingly complex convolutional neural network designs. However, due to the unpredictable domain shift, generalizing trained model to unseen scena…
Crowd CountingPolyFrame at MWE-2026 AdMIRe 2: When Words Are Not Enough: Multimodal Idiom Disambiguation
Multimodal models struggle with idiomatic expressions due to their non-compositional meanings, a challenge amplified in multilingual settings. We introduced PolyFrame, our system for the MWE-2026 AdMIRe2 shared task on m…
Type predictionOn the Robustness of Domain Adaption to Adversarial Attacks
State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial sa…
Adversarial AttackDomain AdaptationPseudo LabelUnsupervised Domain AdaptationPSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation
We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per languag…
Binary ClassificationData Augmentation