DQNC2S: DQN-based Cross-stream Crisis event Summarizer
This addresses the problem of scalable and efficient crisis event summarization for disaster response teams, though it is incremental as it builds on existing DQN methods.
The paper tackles the challenge of summarizing multiple disaster-relevant data streams by proposing an online approach using Deep Q-Networks to select relevant text without human annotations or re-ranking, achieving superior ROUGE and BERTScore results on the CrisisFACTS 2022 benchmark.
Summarizing multiple disaster-relevant data streams simultaneously is particularly challenging as existing Retrieve&Re-ranking strategies suffer from the inherent redundancy of multi-stream data and limited scalability in a multi-query setting. This work proposes an online approach to crisis timeline generation based on weak annotation with Deep Q-Networks. It selects on-the-fly the relevant pieces of text without requiring neither human annotations nor content re-ranking. This makes the inference time independent of the number of input queries. The proposed approach also incorporates a redundancy filter into the reward function to effectively handle cross-stream content overlaps. The achieved ROUGE and BERTScore results are superior to those of best-performing models on the CrisisFACTS 2022 benchmark.