Understanding Class Representations: An Intrinsic Evaluation of Zero-Shot Text Classification

Workshop on Deep Learning for Knowledge Graphs (DL4KG @ ISWC2021)

Hoppe, Fabian and Dessì, Danilo and Sack, Harald

Frequently, Text Classification is limited by insufficient training data. This problem is addressed by Zero-Shot Classification through the inclusion of external class definitions and then exploiting the relations between classes seen during training and unseen classes (Zero-shot). However, it requires a class embedding space capable of accurately representing the semantic relatedness between classes. This work defines an intrinsic evaluation based on greater-than constraints to provide a better understanding of this relatedness. The results imply that textual embeddings are able to capture more semantics than Knowledge Graph embeddings, but combining both modalities yields the best performance.

@inproceedings{hoppe_understanding_2021,
  title = {Understanding {Class} {Representations}: {An} {Intrinsic} {Evaluation} of {Zero}-{Shot} {Text} {Classification}},
  booktitle = {Workshop on {Deep} {Learning} for {Knowledge} {Graphs} ({DL4KG} @ {ISWC2021})},
  author = {Hoppe, Fabian and Dessì, Danilo and Sack, Harald},
  year = {2021}
}