# Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments

arXiv: https://arxiv.org/abs/2110.06865 · HTML: https://mlsanity.com/paper/2110.06865/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 126 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Linguistically-Informed Self-Attention for Semantic Role Labeling](https://mlsanity.com/paper/1804.08199/) (2018)
- [AMR Parsing as Sequence-to-Graph Transduction](https://mlsanity.com/paper/1905.08704/) (2019)
- [Efficient Second-Order TreeCRF for Neural Dependency Parsing](https://mlsanity.com/paper/2005.00975/) (2020)
- [Torch-Struct: Deep Structured Prediction Library](https://mlsanity.com/paper/2002.00876/) (2020)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling](https://mlsanity.com/paper/2012.00857/) (2020)
- [Broad-Coverage Semantic Parsing as Transduction](https://mlsanity.com/paper/1909.02607/) (2019)
- [The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders](https://mlsanity.com/paper/2109.06939/) (2021)
- [Dependency-Guided LSTM-CRF for Named Entity Recognition](https://mlsanity.com/paper/1909.10148/) (2019)
- [Syntactic Scaffolds for Semantic Structures](https://mlsanity.com/paper/1808.10485/) (2018)
- [Learning Structured Text Representations](https://mlsanity.com/paper/1705.09207/) (2017)
- [Deep Semantic Role Labeling with Self-Attention](https://mlsanity.com/paper/1712.01586/) (2017)
- [Nested Named Entity Recognition with Partially-Observed TreeCRFs](https://mlsanity.com/paper/2012.08478/) (2020)
- [Dependency or Span, End-to-End Uniform Semantic Role Labeling](https://mlsanity.com/paper/1901.05280/) (2019)
- [Better Feature Integration for Named Entity Recognition](https://mlsanity.com/paper/2104.05316/) (2021)
- [Second-Order Semantic Dependency Parsing with End-to-End Neural Networks](https://mlsanity.com/paper/1906.07880/) (2019)
- [The Return of Lexical Dependencies: Neural Lexicalized PCFGs](https://mlsanity.com/paper/2007.15135/) (2020)
- [Neural Bi-Lexicalized PCFG Induction](https://mlsanity.com/paper/2105.15021/) (2021)

## Built on by (most cited first, 14 of 14)

- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL](https://mlsanity.com/paper/2405.06410/) (2024)
- [Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model](https://mlsanity.com/paper/2307.14785/) (2023)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language](https://mlsanity.com/paper/2201.10262/) (2022)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing](https://mlsanity.com/paper/2112.02970/) (2021)
- [Structured Sentiment Analysis as Transition-based Dependency Graph Parsing](https://mlsanity.com/paper/2305.05311/) (2023)
- [Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing](https://mlsanity.com/paper/2407.04801/) (2024)
- [LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models](https://mlsanity.com/paper/2506.05385/) (2025)
- [PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation](https://mlsanity.com/paper/2210.06408/) (2022)
- [EDeR: A Dataset for Exploring Dependency Relations Between Events](https://mlsanity.com/paper/2304.01612/) (2023)
- [Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure](https://mlsanity.com/paper/2406.03772/) (2024)

## Abstract (arXiv)

Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite ubiquity, they share some intrinsic drawbacks of not considering internal argument structures, potentially hindering the model's expressiveness. The key challenge is arguments are flat structures, and there are no determined subtree realizations for words inside arguments. To remedy this, in this paper, we propose to regard flat argument spans as latent subtrees, accordingly reducing SRL to a tree parsing task. In particular, we equip our formulation with a novel span-constrained TreeCRF to make tree structures span-aware and further extend it to the second-order case. We conduct extensive experiments on CoNLL05 and CoNLL12 benchmarks. Results reveal that our methods perform favorably better than all previous syntax-agnostic works, achieving new state-of-the-art under both end-to-end and w/ gold predicates settings.