Cross-lingual Transfer Learning for Semantic Role Labeling in Russian
This work is devoted to semantic role labeling (SRL) task in Russian. We investigate the role of transfer learning strategies between English FrameNet and Russian FrameBank corpora. We perform experiments with embeddings obtained from various types of multilingual language models, including BERT, XLM-R, MUSE, and LASER. For evaluation, we use a Russian FrameBank dataset. As source data for transfer learning, we experimented with the full version of FrameNet and the reduced dataset with a smaller number of semantic roles identical to FrameBank. Evaluation results demonstrate that BERT embeddings show the best transfer capabilities. The model with pretraining on the reduced English SRL data and fine-tuning on the Russian SRL data show macro-averaged F1-measure of 79.8%, which is above our baseline of 78.4%.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual TransferSemantic Role LabelingTransfer LearningXLM-RMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cross-lingual Transfer of Semantic Role Labeling Models
Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning
The Natural Language Processing task of determining "Who did what to whom" is called Semantic Role Labeling. For English, recent methods based on Transformer models have allowed for major improvements in this task over t…
Cross-Lingual TransferDependency ParsingSemantic Role LabelingTransfer LearningCross-lingual Semantic Role Labeling with Model Transfer
Prior studies show that cross-lingual semantic role labeling (SRL) can be achieved by model transfer under the help of universal features. In this paper, we fill the gap of cross-lingual SRL by proposing an end-to-end SR…
Semantic Role LabelingOn the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challengin…
Cross-Lingual TransferSemantic Role LabelingA New Method for Cross-Lingual-based Semantic Role Labeling
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.…
Semantic Role Labeling