Named entity recognition using conditional random fields with non-local relational constraints

TL;DR

This paper enhances named entity recognition by integrating non-local relational constraints into conditional random fields, using integer linear programming and Lagrangian relaxation to model long-distance dependencies, with experimental validation.

Contribution

It introduces a novel approach combining CRFs with non-local constraints via ILP and Lagrangian relaxation for improved NER performance.

Findings

Improved accuracy in named entity recognition tasks.

Effective modeling of long-distance relationships in text.

Demonstrated feasibility of complex constraint integration.

Abstract

We begin by introducing the Computer Science branch of Natural Language Processing, then narrowing the attention on its subbranch of Information Extraction and particularly on Named Entity Recognition, discussing briefly its main methodological approaches. It follows an introduction to state-of-the-art Conditional Random Fields under the form of linear chains. Subsequently, the idea of constrained inference as a way to model long-distance relationships in a text is presented, based on an Integer Linear Programming representation of the problem. Adding such relationships to the problem as automatically inferred logical formulas, translatable into linear conditions, we propose to solve the resulting more complex problem with the aid of Lagrangian relaxation, of which some technical details are explained. Lastly, we give some experimental results.