Domain Adaptation of SRL Systems for Biological Processes

@inproceedings{Rajagopal2019DomainAO,
  title={Domain Adaptation of SRL Systems for Biological Processes},
  author={Dheeraj Rajagopal and Nidhi Vyas and Aditya Siddhant and Anirudha Rayasam and Niket Tandon and E. Hovy},
  booktitle={BioNLP@ACL},
  year={2019}
}
Domain adaptation remains one of the most challenging aspects in the wide-spread use of Semantic Role Labeling (SRL) systems. [...] Key Method Our first approach defines a mapping between the source labels and the target labels, and the other approach modifies the final CRF layer in sequence-labeling neural network architecture. We perform our experiments on ProcessBank (Berant et al., 2014) dataset which contains less than 200 paragraphs on biological processes. We improve over the previous state-of-the-art…Expand
Recent Trends in Natural Language Understanding for Procedural Knowledge

References

SHOWING 1-10 OF 36 REFERENCES
Domain adaptation for semantic role labeling in the biomedical domain
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Domain Adaptation in Semantic Role Labeling Using a Neural Language Model and Linguistic Resources
Deep Semantic Role Labeling with Self-Attention
Simple and Effective Semi-Supervised Question Answering
Bidirectional LSTM-CRF Models for Sequence Tagging
...
1
2
3
4
...