Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
Marek Rei, Anders Søgaard · 2018
Can attention-or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels?We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against tokenlevel annotation on four different datasets.Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems.Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.