Interaction Matching for Long-Tail Multi-Label Classification
This addresses the long-tail label issue in multi-label classification for domains like medical coding and software tutorials, offering an incremental enhancement to existing methods.
The paper tackled the problem of bias towards frequent labels in multi-label classification by incorporating interaction matching from ad-hoc search ranking, achieving up to an 11% relative improvement in macro performance, particularly for infrequent labels.
We present an elegant and effective approach for addressing limitations in existing multi-label classification models by incorporating interaction matching, a concept shown to be useful for ad-hoc search result ranking. By performing soft n-gram interaction matching, we match labels with natural language descriptions (which are common to have in most multi-labeling tasks). Our approach can be used to enhance existing multi-label classification approaches, which are biased toward frequently-occurring labels. We evaluate our approach on two challenging tasks: automatic medical coding of clinical notes and automatic labeling of entities from software tutorial text. Our results show that our method can yield up to an 11% relative improvement in macro performance, with most of the gains stemming labels that appear infrequently in the training set (i.e., the long tail of labels).