Improving Chinese SRL with Heterogeneous Annotations

TL;DR

This paper introduces a novel progressive learning model with Gated Recurrent Adapters to improve Chinese semantic role labeling by leveraging heterogeneous annotated corpora, and also releases a new Chinese SRL corpus.

Contribution

The paper proposes a new progressive neural network model that effectively utilizes diverse annotated datasets for Chinese SRL, addressing data sparsity issues.

Findings

Model outperforms state-of-the-art methods on CPB 1.0

Introduces Chinese SemBank corpus for SRL

Demonstrates effective knowledge transfer across heterogeneous data

Abstract

Previous studies on Chinese semantic role labeling (SRL) have concentrated on single semantically annotated corpus. But the training data of single corpus is often limited. Meanwhile, there usually exists other semantically annotated corpora for Chinese SRL scattered across different annotation frameworks. Data sparsity remains a bottleneck. This situation calls for larger training datasets, or effective approaches which can take advantage of highly heterogeneous data. In these papers, we focus mainly on the latter, that is, to improve Chinese SRL by using heterogeneous corpora together. We propose a novel progressive learning model which augments the Progressive Neural Network with Gated Recurrent Adapters. The model can accommodate heterogeneous inputs and effectively transfer knowledge between them. We also release a new corpus, Chinese SemBank, for Chinese SRL. Experiments on CPB 1.0 show that ours model outperforms state-of-the-art methods.