RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU
It addresses the problem of unifying diverse NLU tasks for researchers and practitioners, though it appears incremental by extending existing UIE formulations.
The paper tackles the lack of a unified encoder-based model for Information Extraction (IE) and Text Classification (CLS) in NLU by proposing RexUniNLU, a recursive method with explicit schema constraints that handles various extraction schemas like quadruples and quintuples, and achieves effectiveness in experiments across IE, CLS, and multi-modal tasks.
Information Extraction (IE) and Text Classification (CLS) serve as the fundamental pillars of NLU, with both disciplines relying on analyzing input sequences to categorize outputs into pre-established schemas. However, there is no existing encoder-based model that can unify IE and CLS tasks from this perspective. To fully explore the foundation shared within NLU tasks, we have proposed a Recursive Method with Explicit Schema Instructor for Universal NLU. Specifically, we firstly redefine the true universal information extraction (UIE) with a formal formulation that covers almost all extraction schemas, including quadruples and quintuples which remain unsolved for previous UIE models. Then, we expands the formulation to all CLS and multi-modal NLU tasks. Based on that, we introduce RexUniNLU, an universal NLU solution that employs explicit schema constraints for IE and CLS, which encompasses all IE and CLS tasks and prevent incorrect connections between schema and input sequence. To avoid interference between different schemas, we reset the position ids and attention mask matrices. Extensive experiments are conducted on IE, CLS in both English and Chinese, and multi-modality, revealing the effectiveness and superiority. Our codes are publicly released.