TacoERE: Cluster-aware Compression for Event Relation Extraction

arXiv:2405.06890v1 Announce Type: new
Abstract: Event relation extraction (ERE) is a critical and fundamental challenge for natural language processing. Existing work mainly focuses on directly modeling the entire document, which cannot effectively handle long-range dependencies and information redundancy. To address these issues, we propose a cluster-aware compression method for improving event relation extraction (TacoERE), which explores a compression-then-extraction paradigm. Specifically, we first introduce document clustering for modeling event dependencies. It splits the document into intra- and inter-clusters, where intra-clusters aim …

abstract arxiv challenge cluster compression cs.ai cs.cl dependencies document event extraction fundamental improving information language language processing modeling natural natural language natural language processing processing redundancy type work