mlsanityData to 14 Oct 2026

Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures

arXiv 2212.01094 ↗First posted 2 Dec 2022cs.CL cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

One of the common traits of past and present approaches for Semantic Role Labeling (SRL) is that they rely upon discrete labels drawn from a predefined linguistic inventory to classify predicate senses and their arguments. However, we argue this need not be the case. In this paper, we present an approach that leverages Definition Modeling to introduce a generalized formulation of SRL as the task of describing predicate-argument structures using natural language definitions instead of discrete labels. Our novel formulation takes a first step towards placing interpretability and flexibility foremost, and yet our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance. We release our software for research purposes at https://github.com/SapienzaNLP/dsrl.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 26 of its 70 references that are in the map. First posted on arXiv 2 Dec 2022.

Builds on

26 of 70 references.

References · 26

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  2. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  3. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  4. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 372
  5. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  6. 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
  7. 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 79
  8. 2018Linguistically-Informed Self-Attention for Semantic Role Labelingcited by 71
  9. 2021Visual Semantic Role Labeling for Video Understandingcited by 60
  10. 2016Definition Modeling: Learning to define word embeddings in natural languagecited by 46
  11. 2018Large-Scale QA-SRL Parsingcited by 45
  12. 2018Jointly Predicting Predicates and Arguments in Neural Semantic Role Labelingcited by 34
14 more
  1. 2017Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffoldcited by 33
  2. 2018Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networkscited by 30
  3. 2019Dependency or Span, End-to-End Uniform Semantic Role Labelingcited by 22
  4. 2021End-to-end Semantic Role Labeling with Neural Transition-based Modelcited by 22
  5. 2021Asking It All: Generating Contextualized Questions for any Semantic Rolecited by 22
  6. 2017Learning to Explain Non-Standard English Words and Phrasescited by 21
  7. 2016Neural Semantic Role Labeling with Dependency Path Embeddingscited by 15
  8. 2018A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?cited by 13
  9. 2018Learning Joint Semantic Parsers from Disjoint Datacited by 12
  10. 2019Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labelingcited by 12
  11. 2017A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labelingcited by 10
  12. 2019Syntax-aware Multilingual Semantic Role Labelingcited by 7
  13. 2021A Graph-Based Neural Model for End-to-End Frame Semantic Parsingcited by 7
  14. 2021Sister Help: Data Augmentation for Frame-Semantic Role Labelingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 2.

4 papers.