Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling
This provides a flexible method for augmenting SRL training data in low-resource languages, addressing a domain-specific bottleneck in natural language processing.
The paper tackles the problem of generating semantic role labeling (SRL) annotations for resource-poor languages by proposing a cross-lingual encoder-decoder model that simultaneously translates and labels sentences without needing parallel data at inference, resulting in high-quality sentences and accurate annotations as shown through manual evaluation.
We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not need parallel data during inference time. Our approach can be applied in monolingual, multilingual and cross-lingual settings and is able to produce dependency-based and span-based SRL annotations. We benchmark the labeling performance of our model in different monolingual and multilingual settings using well-known SRL datasets. We then train our model in a cross-lingual setting to generate new SRL labeled data. Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations. Our proposed architecture offers a flexible method for leveraging SRL data in multiple languages.