Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
This addresses scalability issues in relation extraction for natural language processing applications, though it is incremental as it builds on existing pre-trained Transformer models.
The paper tackled the problem of extracting multiple relations from a paragraph by proposing a one-pass method to avoid the computational expense of multiple passes, achieving state-of-the-art performance on the ACE 2005 benchmark.
Most approaches to extraction multiple relations from a paragraph require multiple passes over the paragraph. In practice, multiple passes are computationally expensive and this makes difficult to scale to longer paragraphs and larger text corpora. In this work, we focus on the task of multiple relation extraction by encoding the paragraph only once (one-pass). We build our solution on the pre-trained self-attentive (Transformer) models, where we first add a structured prediction layer to handle extraction between multiple entity pairs, then enhance the paragraph embedding to capture multiple relational information associated with each entity with an entity-aware attention technique. We show that our approach is not only scalable but can also perform state-of-the-art on the standard benchmark ACE 2005.