# Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling

arXiv: https://arxiv.org/abs/1805.04787 · HTML: https://mlsanity.com/paper/1805.04787/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2018.

## Built on by (most cited first, 30 of 34)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2107.12214/) (2021)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders](https://mlsanity.com/paper/2109.06939/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [End-to-end Semantic Role Labeling with Neural Transition-based Model](https://mlsanity.com/paper/2101.00394/) (2021)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Sequential Cross-Document Coreference Resolution](https://mlsanity.com/paper/2104.08413/) (2021)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [A Graph-Based Neural Model for End-to-End Frame Semantic Parsing](https://mlsanity.com/paper/2109.12319/) (2021)
- [Towards Transparent AI: A Survey on Explainable Large Language Models](https://mlsanity.com/paper/2506.21812/) (2025)
- [A Data-Centric Framework for Composable NLP Workflows](https://mlsanity.com/paper/2103.01834/) (2021)
- [Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model](https://mlsanity.com/paper/2307.14785/) (2023)
- [Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures](https://mlsanity.com/paper/2212.01094/) (2022)
- [Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation](https://mlsanity.com/paper/2105.06097/) (2021)
- [Document Embedding for Scientific Articles: Efficacy of Word Embeddings vs TFIDF](https://mlsanity.com/paper/2107.05151/) (2021)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [Towards Transparent AI: A Survey on Explainable Language Models](https://mlsanity.com/paper/2509.21631/) (2025)
- [Argument Linking: A Survey and Forecast](https://mlsanity.com/paper/2107.08523/) (2021)
- [ELIT: Emory Language and Information Toolkit](https://mlsanity.com/paper/2109.03903/) (2021)
- [Graph-Based Decoding for Task Oriented Semantic Parsing](https://mlsanity.com/paper/2109.04587/) (2021)
- [Part & Whole Extraction: Towards A Deep Understanding of Quantitative Facts for Percentages in Text](https://mlsanity.com/paper/2110.13505/) (2021)
- [Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit](https://mlsanity.com/paper/2208.04749/) (2022)
- [Span-based joint entity and relation extraction augmented with sequence tagging mechanism](https://mlsanity.com/paper/2210.12720/) (2022)
- [Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing](https://mlsanity.com/paper/2112.02970/) (2021)
- [DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit](https://mlsanity.com/paper/2310.09501/) (2023)
- [MuLMS: A Multi-Layer Annotated Text Corpus for Information Extraction in the Materials Science Domain](https://mlsanity.com/paper/2310.15569/) (2023)

## Abstract (arXiv)

Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them. The model makes independent decisions about what relationship, if any, holds between every possible word-span pair, and learns contextualized span representations that provide rich, shared input features for each decision. Experiments demonstrate that this approach sets a new state of the art on PropBank SRL without gold predicates.