Make Spoken Document Readable: Leveraging Graph Attention Networks for Chinese Document-Level Spoken-to-Written Simplification

As people use language differently when speaking compared to writing, transcriptions generated by automatic speech recognition systems can be difficult to read. While techniques exist to simplify spoken language into written language at the sentence level, research on simplifying spoken language has various spoken language issues at the document level is limited. Document-level spoken-to-written simplification faces challenges posed by cross-sentence transformations and the long dependencies of spoken documents. This paper proposes a new method called G-DSWS (Graph attention networks for Document-level Spoken-to-Written Simplification) using graph attention networks to model the structure of a document explicitly. G-DSWS utilizes structural information from the document to improve the document modeling capability of the encoder-decoder architecture. Experiments on the internal and publicly available datasets demonstrate the effectiveness of the proposed model. And the human evaluation and case study show that G-DSWS indeed improves spoken Chinese documents’ readability.