Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF

TL;DR

This paper introduces a novel method for named entity recognition that enhances the ability of linear chain CRFs to model long-distance dependencies between entities by using outside labels as a transmission medium, improving performance without increased computational cost.

Contribution

It proposes a precursor-induced CRF that incorporates outside label information to connect distant entities, addressing limitations of first- and second-order CRFs in NER.

Findings

Improved long-distance dependency modeling in CRFs for NER.

Achieved better performance with lower computational loss.

Demonstrated effectiveness through empirical results.

Abstract

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.