A New Method for Cross-Lingual-based Semantic Role Labeling

TL;DR

This paper introduces a deep learning-based cross-lingual semantic role labeling method that significantly outperforms previous models, especially in low-resource language scenarios, by leveraging minimal data and model transfer techniques.

Contribution

The paper presents a novel deep learning approach for cross-lingual semantic role labeling that improves performance with limited training data and surpasses existing models.

Findings

2.05% improvement in monolingual F1-score

6.23% improvement in cross-lingual F1-score

Model outperforms previous approaches significantly

Abstract

Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a deep learning algorithm based on model transfer has been proposed. The algorithm utilizes a dataset consisting of the English portion of CoNLL2009 and a corpus of semantic roles in Persian. To optimize the efficiency of training, only ten percent of the educational data from each language is used. The results of the proposed model demonstrate significant improvements compared to Niksirt et al.'s model. In monolingual mode, the proposed model achieved a 2.05 percent improvement on F1-score, while in cross-lingual mode, the improvement was even more substantial, reaching 6.23 percent. Worth noting is that the compared model only trained two of the four stages of semantic role labeling and employed golden data for the remaining two stages. This suggests that the actual superiority of the proposed model surpasses the reported numbers by a significant margin. The development of cross-lingual methods for semantic role labeling holds promise, particularly in addressing the scarcity of annotated data for various languages. These advancements pave the way for further research in understanding and processing natural language across different linguistic contexts.