# Neural Unsupervised Semantic Role Labeling

arXiv: https://arxiv.org/abs/2104.09047 · HTML: https://mlsanity.com/paper/2104.09047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Dependency or Span, End-to-End Uniform Semantic Role Labeling](https://mlsanity.com/paper/1901.05280/) (2019)
- [Neural Semantic Role Labeling with Dependency Path Embeddings](https://mlsanity.com/paper/1605.07515/) (2016)
- [Parsing All: Syntax and Semantics, Dependencies and Spans](https://mlsanity.com/paper/1908.11522/) (2019)
- [Cross-lingual Annotation Projection for Semantic Roles](https://mlsanity.com/paper/1401.5694/) (2014)
- [High-order Semantic Role Labeling](https://mlsanity.com/paper/2010.04641/) (2020)
- [Syntax-aware Multilingual Semantic Role Labeling](https://mlsanity.com/paper/1909.00310/) (2019)
- [Adaptive Convolution for Semantic Role Labeling](https://mlsanity.com/paper/2012.13939/) (2020)
- [Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework](https://mlsanity.com/paper/1412.2812/) (2014)

## Abstract (arXiv)

The task of semantic role labeling (SRL) is dedicated to finding the predicate-argument structure. Previous works on SRL are mostly supervised and do not consider the difficulty in labeling each example which can be very expensive and time-consuming. In this paper, we present the first neural unsupervised model for SRL. To decompose the task as two argument related subtasks, identification and clustering, we propose a pipeline that correspondingly consists of two neural modules. First, we train a neural model on two syntax-aware statistically developed rules. The neural model gets the relevance signal for each token in a sentence, to feed into a BiLSTM, and then an adversarial layer for noise-adding and classifying simultaneously, thus enabling the model to learn the semantic structure of a sentence. Then we propose another neural model for argument role clustering, which is done through clustering the learned argument embeddings biased towards their dependency relations. Experiments on CoNLL-2009 English dataset demonstrate that our model outperforms previous state-of-the-art baseline in terms of non-neural models for argument identification and classification.