Learning to Recognize Discontiguous Entities
This addresses the challenge of entity recognition in natural language processing, particularly for discontiguous entities, which is an incremental improvement over existing methods like linear-chain CRFs.
The paper tackles the problem of recognizing discontiguous entities by proposing a hypergraph representation to jointly encode such entities of unbounded length that can overlap, achieving significantly better results on standard data with many discontiguous entities.
This paper focuses on the study of recognizing discontiguous entities. Motivated by a previous work, we propose to use a novel hypergraph representation to jointly encode discontiguous entities of unbounded length, which can overlap with one another. To compare with existing approaches, we first formally introduce the notion of model ambiguity, which defines the difficulty level of interpreting the outputs of a model, and then formally analyze the theoretical advantages of our model over previous existing approaches based on linear-chain CRFs. Our empirical results also show that our model is able to achieve significantly better results when evaluated on standard data with many discontiguous entities.