LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
This addresses the problem of limited mixup applicability in NLP for researchers and practitioners, offering a novel interpolation method that is incremental over prior heuristic-based approaches.
The paper tackles the challenge of applying mixup data augmentation to NLP by proposing LINDA, an unsupervised learning method that interpolates between sentences without heuristics or manual resources, leading to improved generalization in text classification both in-domain and out-of-domain.
Despite the success of mixup in data augmentation, its applicability to natural language processing (NLP) tasks has been limited due to the discrete and variable-length nature of natural languages. Recent studies have thus relied on domain-specific heuristics and manually crafted resources, such as dictionaries, in order to apply mixup in NLP. In this paper, we instead propose an unsupervised learning approach to text interpolation for the purpose of data augmentation, to which we refer as "Learning to INterpolate for Data Augmentation" (LINDA), that does not require any heuristics nor manually crafted resources but learns to interpolate between any pair of natural language sentences over a natural language manifold. After empirically demonstrating the LINDA's interpolation capability, we show that LINDA indeed allows us to seamlessly apply mixup in NLP and leads to better generalization in text classification both in-domain and out-of-domain.