Researchers have developed a new hierarchical strategy using the BART model to improve abstractive multi-document summarization for Vietnamese text. This approach condenses individual documents before aggregating and summarizing them, with a novel method that uses the golden summary to guide document shortening. The technique achieved a ROUGE2-F1 score of 0.2468 on the VLSP 2022 test set and has made additional training data available to the community. AI
IMPACT This research offers a novel approach to abstractive summarization for low-resource languages, potentially improving information access.
RANK_REASON The cluster contains an academic paper detailing a new methodology for a specific NLP task.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
