HELD: Hierarchical entity-label disambiguation in named entity recognition task using deep learning

Abstract

Named Entity Recognition (NER) is a challenging learning task of identifying and classifying entity mentions in texts into predefined categories. In recent years, deep learning (DL) methods empowered by distributed representations, such as word- and character-level embeddings, have been employed in NER systems. However, for information extraction in Police narrative reports, the performance of a DL-based NER approach is limited due to the presence of fine-grained ambiguous entities. For example, given the narrative report “Anna stole Ada’s car”, imagine that we intend to identify the VICTIM and the ROBBER, two sub-labels of PERSON. Traditional NER systems have limited performance in categorizing entity labels arranged in a hierarchical structure. Furthermore, it is unfeasible to obtain information from knowledge bases to give a disambiguated meaning between the entity mentions and the actual labels. This information must be extracted directly from the context dependencies. In this paper, we deal with the Hierarchical Entity-Label Disambiguation problem in Police reports without the use of knowledge bases. To tackle such a problem, we present HELD, an ensemble model that combines two components for NER: a BLSTM-CRF architecture and a NER tool. Experiments conducted on a real Police reports dataset show that HELD significantly outperforms baseline approaches.

An Event Extraction Approach Based on a Multi-Round Q&A Framework

“…The current event extraction methods proposed by scholars at home and abroad are mainly classified as the following: pattern-matching based [4], machine-learning based [5], and deep-learning based [6].…”

Processamento de Linguagem Natural via Aprendizagem Profunda

“…Além de seu tamanho, o brWaC é composto de documentos inteiros e sua metodologia garante alta diversidade de domínio e qualidade de conteúdo. A quantidade de parâmetros e dados, e o fato de precisarem de processadores avançados para treino do BERT e de outros LMs, tratam-se das principais limitações existentes hoje para obtenção de word embeddings contextuais [Neves Oliveira et al 2022].…”

“…Os projetos de Pesquisa e Desenvolvimento em parceria com alguns departamentos de Segurança Pública envolviam: (i) tarefa de Reconhecimento de Entidade Nomeada (NER), para extração das informações relevantes das narrativas de BOs, como vítimas, criminosos e testemunhas; (ii) problema de Classificação de Textos a partir das narrativas dos BOs, para categorizar em um tipo de crime, como furto, fraude ou roubo; (iii) e, dado um BO, como identificar outros que apresentem narrativas semelhantes na base de dados da Segurança Pública, de forma que sejam identificados crimes com o mesmo modus operandi. [Neves Oliveira et al 2022, Zschornack R. S. et al 2020, da Silva et al 2019] são alguns dos trabalhos publicados nessa temática.…”