Abstract
In this work, we enhance higher-order graph-based approaches for span-based semantic role labeling (SRL) by means of structured modeling. To decrease the complexity of higher-order modeling, we decompose the edge from predicate word to argument span into three different edges, predicate-to-head (P2H), predicate-to-tail (P2T), and head-to-tail (H2T), where head/tail means the first/last word of the semantic argument span. As such, we use a CRF-based higher-order dependency parser and leverage Mean-Field Variational Inference (MFVI) for higher-order inference. Moreover, since semantic arguments of predicates are often constituents within a constituency parse tree, we can leverage such nice structural property by defining a TreeCRF distribution over all H2T edges, using the idea of partial marginalization to define structural training loss. We further leverage structured MFVI to enhance inference. We experiment on span-based SRL benchmarks, showing the effectiveness of both higher-order and structured modeling and the combination thereof. In addition, we show superior performance of structured MFVI against vanilla MFVI.- Anthology ID:
- 2023.findings-acl.58
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 918–931
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.58
- DOI:
- Cite (ACL):
- Wei Liu, Songlin Yang, and Kewei Tu. 2023. Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role. In Findings of the Association for Computational Linguistics: ACL 2023, pages 918–931, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role (Liu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.findings-acl.58.pdf