Jul 14, 2023 · In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data from existing examples by ...

Aug 11, 2024 · In this paper, we propose Chain-of-Thought Attribute. Manipulation (CoTAM), a novel approach that generates new data from existing examples by ...

Official Implementation of the ACL2024 Findings paper "Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation".

Results on various tasks, such as text (pair) classification, aspect-based sentiment analysis, and conditional text generation, verify the superiority of ...

Sep 24, 2024 · Bibliographic details on Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation.

May 23, 2024 · This paper introduces a novel approach called Chain-of-Thought Attribute Manipulation (CoTAM) for data augmentation in few-shot NLP tasks.

Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose ...

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation Letian Peng, Yuwei Zhang, Jingbo Shang; Match More ...

As shown in Figure 1, controlled attribute manipulation can efficiently find accurate decision boundaries since (1) we directly manipulate along the direction ...

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation Letian Peng, Yuwei Zhang and Jingbo Shang. ACL ...