Open Vocabulary Extreme Classification Using Generative Models
This addresses the need for more flexible tagging systems in real-world applications where predefined labels are often insufficient, though it is an incremental advancement over existing XMC methods.
The paper tackles the problem of incomplete label sets in extreme multi-label classification by introducing open vocabulary XMC, where models must predict both known and novel labels; the proposed GROOV model performs on par with state-of-the-art methods for known labels while generating meaningful new ones.
The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary tags. However in real world scenarios this label set, although large, is often incomplete and experts frequently need to refine it. To develop systems that simplify this process, we introduce the task of open vocabulary XMC (OXMC): given a piece of content, predict a set of labels, some of which may be outside of the known tag set. Hence, in addition to not having training data for some labels - as is the case in zero-shot classification - models need to invent some labels on-the-fly. We propose GROOV, a fine-tuned seq2seq model for OXMC that generates the set of labels as a flat sequence and is trained using a novel loss independent of predicted label order. We show the efficacy of the approach, experimenting with popular XMC datasets for which GROOV is able to predict meaningful labels outside the given vocabulary while performing on par with state-of-the-art solutions for known labels.