CRF+LG: A Hybrid Approach for the Portuguese Named Entity Recognition

Pirovani, Juliana P. C.; Oliveira, Elias

doi:10.1007/978-3-319-76348-4_11

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison between four tools to recognize NEs in Portuguese texts [2] suggested that the rule-based approach is the most effective for person names. Recently, LGs have been successfully integrated in a hybrid approach to Portuguese NER [12].…”

Section: Introductionmentioning

confidence: 99%

Concordance Comparison as a Means of Assembling Local Grammars

Pirovani

Oliveira

Laporte³

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Named Entity Recognition for person names is an important but non-trivial task in information extraction. This article uses a tool that compares the concordances obtained from two local grammars (LG) and highlights the differences. We used the results as an aid to select the best of a set of LGs. By analyzing the comparisons, we observed relationships of inclusion, intersection and disjunction within each pair of LGs, which helped us to assemble those that yielded the best results. This approach was used in a case study on extraction of person names from texts written in Portuguese. We applied the enhanced grammar to the Gold Collection of the Second HAREM. The F-Measure obtained was 76.86, representing a gain of 6 points in relation to the state-of-the-art for Portuguese.

show abstract

Section: Introductionmentioning

confidence: 99%

Concordance Comparison as a Means of Assembling Local Grammars

Pirovani

Oliveira

Laporte³

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…O reconhecimento de entidades nomeadas (Named Entity Recognition -NER) tem como objetivo identificar e classificar automaticamente entidades como pessoas, locais e organizac ¸ões e é uma tarefa importante em Extrac ¸ão de Informac ¸ão. As abordagens utilizadas no desenvolvimento de sistemas de NER são: linguística, aprendizado de máquina ou híbrida [Pirovani and Oliveira 2018].…”

Section: Reconhecimento De Entidades Nomeadasunclassified

“…artigo foi utilizado o modelo híbrido CRF+LG [Pirovani and Oliveira 2018], que se baseia no Conditional Random Fields (CRF), uma estrutura probabilística para realizar a marcac ¸ão e segmentac ¸ão de dados de sequência [Lafferty et al 2001]. Neste modelo híbrido, os autores construíram uma Gramática Local (Local Grammar -LG) para auxiliar o CRF a reconhecer as 10 categorias de entidades nomeadas do HAREM 2 .…”

Section: Nesteunclassified

A Extração de Entidades Nomeadas em Bulas de Medicamentos e em Relatos de Casos Clínicos

Colombo,

Oliveira

2024

Anais Do XXIV Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2024)

View full text Add to dashboard Cite

As bulas farmacêuticas são documentos com informações sobre medicamentos como a sua posologia, as reações adversas, dentre outras informações. Os relatos de casos clínicos são narrativas descritivas e detalhadas das experiências médicas com pacientes. A proposta deste artigo é apresentar e descrever o método de trabalho utilizado para a Extração de Informação automática das bulas farmacêuticas e de relatos de casos clínicos através do Reconhecimento de Entidades Nomeadas. Um modelo de Inteligência Artificial foi treinado a partir de uma abordagem híbrida baseada em Conditional Random Fields (CRF) e Local Grammar (LG), denominada CRF+LG. Os resultados obtidos em medida F1 nos testes com as bulas foram de 94.85% na extração das entidades sobre doenças e 68.63% na extração das entidades sobre medicamentos. Os resultados obtidos nos testes com os relatos de casos clínicos foram de 77.42% na extração das entidades sobre doenças e 87.34% na extração das entidades sobre medicamentos. Os resultados demonstraram que a iniciativa apresentada pode contribuir para auxiliar profissionais de saúde na extração de informações de bulas e de relatos de casos clínicos.

show abstract

“…As well as the rest of NLP tasks and algorithms, the development of methods and resources for Portuguese are increasing day by day. Some important examples are HAREM and Second HAREM [32], Linguakit [13], or SIEMÊS [33] algorithms and resources for unsupervised named entity recognition, joint with well-known suites such as FreeLing [34] or Standford CoreNLP [35] for Portuguese and related supervised initiatives based on conditional random fields [36]. It is important to mention here similar works only focused on semantic relation extraction [37].…”

Section: Unsupervised Information Extraction In Portuguese: Linguakitmentioning

confidence: 99%

Assisting Forensic Identification through Unsupervised Information Extraction of Free Text Autopsy Reports: The Disappearances Cases during the Brazilian Military Dictatorship

2019

View full text Add to dashboard Cite

Anthropological, archaeological, and forensic studies situate enforced disappearance as a strategy associated with the Brazilian military dictatorship (1964–1985), leaving hundreds of persons without identity or cause of death identified. Their forensic reports are the only existing clue for people identification and detection of possible crimes associated with them. The exchange of information among institutions about the identities of disappeared people was not a common practice. Thus, their analysis requires unsupervised techniques, mainly due to the fact that their contextual annotation is extremely time-consuming, difficult to obtain, and with high dependence on the annotator. The use of these techniques allows researchers to assist in the identification and analysis in four areas: Common causes of death, relevant body locations, personal belongings terminology, and correlations between actors such as doctors and police officers involved in the disappearances. This paper analyzes almost 3000 textual reports of missing persons in São Paulo city during the Brazilian dictatorship through unsupervised algorithms of information extraction in Portuguese, identifying named entities and relevant terminology associated with these four criteria. The analysis allowed us to observe terminological patterns relevant for people identification (e.g., presence of rings or similar personal belongings) and automate the study of correlations between actors. The proposed system acts as a first classificatory and indexing middleware of the reports and represents a feasible system that can assist researchers working in pattern search among autopsy reports.

show abstract

CRF+LG: A Hybrid Approach for the Portuguese Named Entity Recognition

Cited by 7 publications

References 9 publications

Concordance Comparison as a Means of Assembling Local Grammars

Concordance Comparison as a Means of Assembling Local Grammars

A Extração de Entidades Nomeadas em Bulas de Medicamentos e em Relatos de Casos Clínicos

Assisting Forensic Identification through Unsupervised Information Extraction of Free Text Autopsy Reports: The Disappearances Cases during the Brazilian Military Dictatorship

Contact Info

Product

Resources

About