Towards Open-Domain Topic Classification
This addresses the need for flexible, real-time text classification for users in dynamic domains, though it is incremental as it builds on existing zero-shot and weakly-supervised methods.
The paper tackles the problem of open-domain topic classification by introducing a zero-shot system that allows real-time user-defined taxonomies, achieving significant improvements over existing zero-shot baselines and competitive performance with weakly-supervised in-domain models across four diverse datasets.
We introduce an open-domain topic classification system that accepts user-defined taxonomy in real time. Users will be able to classify a text snippet with respect to any candidate labels they want, and get instant response from our web interface. To obtain such flexibility, we build the backend model in a zero-shot way. By training on a new dataset constructed from Wikipedia, our label-aware text classifier can effectively utilize implicit knowledge in the pretrained language model to handle labels it has never seen before. We evaluate our model across four datasets from various domains with different label sets. Experiments show that the model significantly improves over existing zero-shot baselines in open-domain scenarios, and performs competitively with weakly-supervised models trained on in-domain data.