Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation
This addresses the problem of generating text in multiple languages from the same input for NLG systems, with incremental improvements over prior delexicalisation methods.
The paper tackled the challenge of multilingual concept-to-text NLG by proposing Language Agnostic Delexicalisation, which uses multilingual embeddings and character-level post-editing to improve generalization across languages, showing that multilingual models outperform monolingual ones and the framework excels in low-resource settings.
Concept-to-text Natural Language Generation is the task of expressing an input meaning representation in natural language. Previous approaches in this task have been able to generalise to rare or unseen instances by relying on a delexicalisation of the input. However, this often requires that the input appears verbatim in the output text. This poses challenges in multilingual settings, where the task expands to generate the output text in multiple languages given the same input. In this paper, we explore the application of multilingual models in concept-to-text and propose Language Agnostic Delexicalisation, a novel delexicalisation method that uses multilingual pretrained embeddings, and employs a character-level post-editing model to inflect words in their correct form during relexicalisation. Our experiments across five datasets and five languages show that multilingual models outperform monolingual models in concept-to-text and that our framework outperforms previous approaches, especially for low resource languages.