Neural Unsupervised Semantic Role Labeling
This addresses the challenge of expensive and time-consuming manual labeling for SRL, offering an unsupervised approach that could benefit NLP researchers and practitioners, though it is incremental as it builds on existing SRL frameworks.
The paper tackles the problem of semantic role labeling (SRL) by proposing the first neural unsupervised model, which decomposes the task into argument identification and clustering using two neural modules, and it outperforms previous non-neural state-of-the-art baselines on the CoNLL-2009 English dataset.
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.