Relation detection between named entities

Abstract

In this paper we describe the first evaluation contest (track) for Portuguese whose goal was to detect and classify relations between named entities in running text, called ReRelEM. Given a collection annotated with named entities belonging to ten different semantic categories, we marked all relationships between them within each document. We used the following fourfold relationship classification: identity, included-in, located-in, and other (which was later on explicitly detailed into twenty different relations). We provide a quantitative description of this evaluation resource, as well as describe the evaluation architecture and summarize the results of the participating systems in the track.

German BERT Model for Legal Named Entity Recognition

“…The impact of intradomain fine-tuning of deep language models, namely ELMo (Sarzynska-Wawer et al, 2021) and BERT, for Legal NER in Portuguese was studied by (Bonifacio et al, 2020). The authors evaluated language models on three different NER tasks, HAREM (Freitas et al, 2010), LeNER-Br (Luz de Araujo et al, 2018), and DrugSeizures-Br 3 . As for the methodology of their experiments, the authors fine-tuned deep LMs pretrained on generaldomain corpus on a legal-domain corpus, and supervised training was done on a NER task.…”

Pais, filhos e outras relações familiares no DIP

“…No ReReLEM (Freitas et al, 2009), a tarefa de identificação de relações entre entidades mencionadas na avaliação do Segundo HAREM 11 , algumas das relações identificadas eram de família, mas não foram tratadas de forma especial, sendo apenas um dos tipos de relação entre entidades, não sendo pedido para marcar especificamente o tipo de relação familiar. 12 Dos 10 sistemas par-ticipantes no Segundo HAREM, apenas 3 participaram na pista do ReRelEM.…”

Identifying Literary Characters in Portuguese

“…As to named entity recognition in Portuguese, there has been significant work in (among others) person name recognition in HAREM [10], and also some form of identification among different denominations in ReRELEM [3] a decade ago. As to distant reading in Portuguese, cf.…”