PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese

TL;DR

This paper introduces PAMPO, a simple and efficient Portuguese named entity recognition algorithm that combines pattern matching, POS tagging, and lexical rules, showing improved recall and F1 scores over existing methods.

Contribution

The paper presents PAMPO, a novel NER method for Portuguese that outperforms current alternatives in recall and F1, with potential applicability to other languages.

Findings

PAMPO significantly improves recall and F1 scores in Portuguese NER tasks.

PAMPO is flexible and potentially adaptable to other languages.

Compared to Alchemy, Zemanta, and Rembrandt, PAMPO shows superior performance.

Abstract

This paper deals with the entity extraction task (named entity recognition) of a text mining process that aims at unveiling non-trivial semantic structures, such as relationships and interaction between entities or communities. In this paper we present a simple and efficient named entity extraction algorithm. The method, named PAMPO (PAttern Matching and POs tagging based algorithm for NER), relies on flexible pattern matching, part-of-speech tagging and lexical-based rules. It was developed to process texts written in Portuguese, however it is potentially applicable to other languages as well. We compare our approach with current alternatives that support Named Entity Recognition (NER) for content written in Portuguese. These are Alchemy, Zemanta and Rembrandt. Evaluation of the efficacy of the entity extraction method on several texts written in Portuguese indicates a considerable improvement on $recall$ and $F_1$ measures.