MARS: Multilingual Aspect-centric Review Summarisation
It addresses the challenge of aggregating and understanding customer sentiment across multiple languages for businesses, which is incremental as it builds on existing summarization methods.
The paper tackled the problem of summarizing multilingual customer reviews at the aspect level to provide actionable insights, and the result showed substantial improvements over abstractive baselines with enhanced efficiency for real-time systems.
Summarizing customer feedback to provide actionable insights for products/services at scale is an important problem for businesses across industries. Lately, the review volumes are increasing across regions and languages, therefore the challenge of aggregating and understanding customer sentiment across multiple languages becomes increasingly vital. In this paper, we propose a novel framework involving a two-step paradigm \textit{Extract-then-Summarise}, namely MARS to revolutionise traditions and address the domain agnostic aspect-level multilingual review summarisation. Extensive automatic and human evaluation shows that our approach brings substantial improvements over abstractive baselines and efficiency to real-time systems.