Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields

Authors

  • Chaoyi Ai School of Information Science and Technology, ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging
  • Kewei Tu School of Information Science and Technology, ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging

DOI:

https://doi.org/10.1609/aaai.v38i16.29715

Keywords:

NLP: Sentence-level Semantics, Textual Inference, etc., NLP: Information Extraction, NLP: Syntax -- Tagging, Chunking & Parsing

Abstract

This paper presents an approach to frame semantic role labeling (FSRL), a task in natural language processing that identifies semantic roles within a text following the theory of frame semantics. Unlike previous approaches which do not adequately model correlations and interactions amongst arguments, we propose arbitrary-order conditional random fields (CRFs) that are capable of modeling full interaction amongst an arbitrary number of arguments of a given predicate. To achieve tractable representation and inference, we apply canonical polyadic decomposition to the arbitrary-order factor in our proposed CRF and utilize mean-field variational inference for approximate inference. We further unfold our iterative inference procedure into a recurrent neural network that is connected to our neural encoder and scorer, enabling end-to-end training and inference. Finally, we also improve our model with several techniques such as span-based scoring and decoding. Our experiments show that our approach achieves state-of-the-art performance in FSRL.

Published

2024-03-24

How to Cite

Ai, C., & Tu, K. (2024). Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17638-17646. https://doi.org/10.1609/aaai.v38i16.29715

Issue

Section

AAAI Technical Track on Natural Language Processing I