Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization
This work addresses fact extraction from multiple disaster-related streams, but it is incremental as it builds on established frameworks like ILP and MMR.
The authors tackled multi-query focused summarization for disaster event tracking by combining retrieval, reranking, and extractive summarization methods, achieving strong results in automatic evaluations.
The CrisisFACTS Track aims to tackle challenges such as multi-stream fact-finding in the domain of event tracking; participants' systems extract important facts from several disaster-related events while incorporating the temporal order. We propose a combination of retrieval, reranking, and the well-known Integer Linear Programming (ILP) and Maximal Marginal Relevance (MMR) frameworks. In the former two modules, we explore various methods including an entity-based baseline, pre-trained and fine-tuned Question Answering systems, and ColBERT. We then use the latter module as an extractive summarization component by taking diversity and novelty criteria into account. The automatic scoring runs show strong results across the evaluation setups but also reveal shortcomings and challenges.