Span-Based Semantic Role Labeling with Argument Pruning and Second-Order Inference
Keywords:Speech & Natural Language Processing (SNLP)
AbstractWe study graph-based approaches to span-based semantic role labeling. This task is difficult due to the need to enumerate all possible predicate-argument pairs and the high degree of imbalance between positive and negative samples. Based on these difficulties, high-order inference that considers interactions between multiple arguments and predicates is often deemed beneficial but has rarely been used in span-based semantic role labeling. Because even for second-order inference, there are already O(n^5) parts for a sentence of length n, and exact high-order inference is intractable. In this paper, we propose a framework consisting of two networks: a predicate-agnostic argument pruning network that reduces the number of candidate arguments to O(n), and a semantic role labeling network with an optional second-order decoder that is unfolded from an approximate inference algorithm. Our experiments show that our framework achieves significant and consistent improvement over previous approaches.
How to Cite
Jia, Z., Yan, Z., Wu, H., & Tu, K. (2022). Span-Based Semantic Role Labeling with Argument Pruning and Second-Order Inference. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10822-10830. https://doi.org/10.1609/aaai.v36i10.21328
AAAI Technical Track on Speech and Natural Language Processing