Neural Unsupervised Semantic Role Labeling

TL;DR

This paper introduces the first neural unsupervised approach to semantic role labeling, decomposing the task into argument identification and clustering, and demonstrating superior performance over previous non-neural methods.

Contribution

It presents a novel neural unsupervised model for SRL that combines syntax-aware rules, neural modules, and clustering of argument embeddings.

Findings

Outperforms previous non-neural SRL models on CoNLL-2009 dataset

Effectively learns semantic structures without labeled data

Demonstrates the viability of neural unsupervised SRL methods

Abstract

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.