Domain Adaptation of SRL Systems for Biological Processes
Citations Over Time
Abstract
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 lowresource domain-specific settings. In this paper, we propose two approaches for domain adaptation in biological domain that involve 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 Pro-cessBank 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.
Related Papers
- → Visual Domain Adaptation by Consensus-Based Transfer to Intermediate Domain(2020)7 cited
- → Learning under Unknown Bias(2013)
- → MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition(2023)
- → DASA: Domain Adaptation via Saliency Augmentation(2023)
- → Collaborative Multi-source Domain Adaptation Through Optimal Transport(2024)