mlsanityData to 7 Oct 2026

A Graph-Based Neural Model for End-to-End Frame Semantic Parsing

arXiv 2109.12319 ↗First posted 25 Sep 2021cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labeling. The three subtasks are closely related while previous studies model them individually, which ignores their intern connections and meanwhile induces error propagation problem. In this work, we propose an end-to-end neural model to tackle the task jointly. Concretely, we exploit a graph-based method, regarding frame semantic parsing as a graph construction problem. All predicates and roles are treated as graph nodes, and their relations are taken as graph edges. Experiment results on two benchmark datasets of frame semantic parsing show that our method is highly competitive, resulting in better performance than pipeline models.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 42 references that are in the map. First posted on arXiv 25 Sep 2021.

Builds on

17 of 42 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  3. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  4. 2015Training Very Deep Networkscited by 172
  5. 2016Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representationscited by 55
  6. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  7. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
  8. 2018Jointly Predicting Predicates and Arguments in Neural Semantic Role Labelingcited by 34
  9. 2017Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffoldcited by 33
  10. 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
  11. 2018Syntactic Scaffolds for Semantic Structurescited by 27
  12. 2019Dependency or Span, End-to-End Uniform Semantic Role Labelingcited by 22
5 more
  1. 2018A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?cited by 13
  2. 2018Learning Joint Semantic Parsers from Disjoint Datacited by 12
  3. 2019Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labelingcited by 12
  4. 2020Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networkscited by 7
  5. 2020High-order Refining for End-to-end Chinese Semantic Role Labelingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 1; 2026: 2.

7 papers.

  1. 2022Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structurescited by 4
  2. 2025Can LLMs Extract Frame-Semantic Arguments?cited by 3
  3. 2022Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labelingcited by 2
  4. 2024Annotating FrameNet via Structure-Conditioned Language Generationcited by 2
  5. 2023Persian Semantic Role Labeling Using Transfer Learning and BERT-Based Modelscited by 1
  6. 2026FrameNet Semantic Role Classification by Analogycited by 0
  7. 2026The Multilingual FrameNet Corpuscited by 0