SimCSum: Joint Learning of Simplification and Cross-lingual Summarization for Cross-lingual Science Journalism
This addresses the need for accessible science journalism for non-expert audiences in different languages, representing an incremental advance through multi-task learning.
The paper tackles the problem of generating cross-lingual popular science summaries by jointly training simplification and cross-lingual summarization tasks, resulting in statistically significant improvements over state-of-the-art methods on two non-synthetic datasets.
Cross-lingual science journalism generates popular science stories of scientific articles different from the source language for a non-expert audience. Hence, a cross-lingual popular summary must contain the salient content of the input document, and the content should be coherent, comprehensible, and in a local language for the targeted audience. We improve these aspects of cross-lingual summary generation by joint training of two high-level NLP tasks, simplification and cross-lingual summarization. The former task reduces linguistic complexity, and the latter focuses on cross-lingual abstractive summarization. We propose a novel multi-task architecture - SimCSum consisting of one shared encoder and two parallel decoders jointly learning simplification and cross-lingual summarization. We empirically investigate the performance of SimCSum by comparing it with several strong baselines over several evaluation metrics and by human evaluation. Overall, SimCSum demonstrates statistically significant improvements over the state-of-the-art on two non-synthetic cross-lingual scientific datasets. Furthermore, we conduct an in-depth investigation into the linguistic properties of generated summaries and an error analysis.