# Towards Semi-Supervised Learning for Deep Semantic Role Labeling

arXiv: https://arxiv.org/abs/1808.09543 · HTML: https://mlsanity.com/paper/1808.09543/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 8 of 8)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [NeuPSL: Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2205.14268/) (2022)
- [Improved Latent Tree Induction with Distant Supervision via Span Constraints](https://mlsanity.com/paper/2109.05112/) (2021)
- [Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2403.17853/) (2024)
- [PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2110.07415/) (2021)
- [Improve Event Extraction via Self-Training with Gradient Guidance](https://mlsanity.com/paper/2205.12490/) (2022)
- [DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection](https://mlsanity.com/paper/2407.09283/) (2024)
- [An Analysis under a Unified Fomulation of Learning Algorithms with Output Constraints](https://mlsanity.com/paper/2406.01647/) (2024)

## Abstract (arXiv)

Neural models have shown several state-of-the-art performances on Semantic Role Labeling (SRL). However, the neural models require an immense amount of semantic-role corpora and are thus not well suited for low-resource languages or domains. The paper proposes a semi-supervised semantic role labeling method that outperforms the state-of-the-art in limited SRL training corpora. The method is based on explicitly enforcing syntactic constraints by augmenting the training objective with a syntactic-inconsistency loss component and uses SRL-unlabeled instances to train a joint-objective LSTM. On CoNLL-2012 English section, the proposed semi-supervised training with 1%, 10% SRL-labeled data and varying amounts of SRL-unlabeled data achieves +1.58, +0.78 F1, respectively, over the pre-trained models that were trained on SOTA architecture with ELMo on the same SRL-labeled data. Additionally, by using the syntactic-inconsistency loss on inference time, the proposed model achieves +3.67, +2.1 F1 over pre-trained model on 1%, 10% SRL-labeled data, respectively.