Non-Parametric Memory Guidance for Multi-Document Summarization
This work addresses the challenge of insufficient source documents for multi-document summarization in NLP, but it appears incremental as it builds on existing retrieval and generation techniques without claiming major breakthroughs.
The authors tackled the problem of generating qualitative summaries from multiple source documents in multi-document summarization by proposing a retriever-guided model with non-parametric memory, which retrieves relevant candidates from a database and generates summaries using a copy mechanism, though no concrete results or numbers are provided.
Multi-document summarization (MDS) is a difficult task in Natural Language Processing, aiming to summarize information from several documents. However, the source documents are often insufficient to obtain a qualitative summary. We propose a retriever-guided model combined with non-parametric memory for summary generation. This model retrieves relevant candidates from a database and then generates the summary considering the candidates with a copy mechanism and the source documents. The retriever is implemented with Approximate Nearest Neighbor Search (ANN) to search large databases. Our method is evaluated on the MultiXScience dataset which includes scientific articles. Finally, we discuss our results and possible directions for future work.