%0 Conference Proceedings %T Domain Adaptation of SRL Systems for Biological Processes %A Rajagopal, Dheeraj %A Vyas, Nidhi %A Siddhant, Aditya %A Rayasam, Anirudha %A Tandon, Niket %A Hovy, Eduard %Y Demner-Fushman, Dina %Y Cohen, Kevin Bretonnel %Y Ananiadou, Sophia %Y Tsujii, Junichi %S Proceedings of the 18th BioNLP Workshop and Shared Task %D 2019 %8 August %I Association for Computational Linguistics %C Florence, Italy %F rajagopal-etal-2019-domain %X Domain adaptation remains one of the most challenging aspects in the wide-spread use of Semantic Role Labeling (SRL) systems. Current state-of-the-art methods are typically trained on large-scale datasets, but their performances do not directly transfer to low-resource domain-specific settings. In this paper, we propose two approaches for domain adaptation in the biological domain that involves pre-training LSTM-CRF based on existing large-scale datasets and adapting it for a low-resource corpus of biological processes. 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 dataset which contains less than 200 paragraphs on biological processes. We improve over the previous state-of-the-art system on this dataset by 21 F1 points. We also show that, by incorporating event-event relationship in ProcessBank, we are able to achieve an additional 2.6 F1 gain, giving us possible insights into how to improve SRL systems for biological process using richer annotations. %R 10.18653/v1/W19-5009 %U https://aclanthology.org/W19-5009 %U https://doi.org/10.18653/v1/W19-5009 %P 80-87