Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF
This addresses a specific bottleneck in NER for NLP applications, but it is incremental as it builds upon existing CRF methods.
The paper tackles the problem of capturing long-distance dependencies between named entities in NER by designing a high-order dependency factor for linear chain CRFs, resulting in improved performance with reduced computational loss compared to second-order CRFs.
This paper presents a method of designing specific high-order dependency factor on the linear chain conditional random fields (CRFs) for named entity recognition (NER). Named entities tend to be separated from each other by multiple outside tokens in a text, and thus the first-order CRF, as well as the second-order CRF, may innately lose transition information between distant named entities. The proposed design uses outside label in NER as a transmission medium of precedent entity information on the CRF. Then, empirical results apparently demonstrate that it is possible to exploit long-distance label dependency in the original first-order linear chain CRF structure upon NER while reducing computational loss rather than in the second-order CRF.