Joint Constrained Learning for Event-Event Relation Extraction
This work addresses the challenge of understanding complex event interactions in natural language processing, offering an incremental improvement by replacing expensive global inference with a more efficient learning-based approach.
The paper tackled the problem of extracting event-event relations, such as temporal order and membership, by proposing a joint constrained learning framework that enforces logical constraints as differentiable objectives, resulting in outperforming state-of-the-art methods on benchmarks for temporal relation extraction and event hierarchy construction.
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving among them. Due to the lack of jointly labeled data for these relational phenomena and the restriction on the structures they articulate, we propose a joint constrained learning framework for modeling event-event relations. Specifically, the framework enforces logical constraints within and across multiple temporal and subevent relations by converting these constraints into differentiable learning objectives. We show that our joint constrained learning approach effectively compensates for the lack of jointly labeled data, and outperforms SOTA methods on benchmarks for both temporal relation extraction and event hierarchy construction, replacing a commonly used but more expensive global inference process. We also present a promising case study showing the effectiveness of our approach in inducing event complexes on an external corpus.