Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
MetadataShow full item record
Rei, M., & Søgaard, A. Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens. The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. https://doi.org/10.17863/CAM.35110
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 token-level 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.
Cambridge Assessment (unknown)
External DOI: https://doi.org/10.17863/CAM.35110
This record's URL: https://www.repository.cam.ac.uk/handle/1810/287795