ICRC-DSEDL: A Film Named Entity Discovery and Linking System Based on Knowledge Bases

2016 ◽  
pp. 205-213
Author(s):  
YaHui Zhao ◽  
Haodi Li ◽  
Qingcai Chen ◽  
Jianglu Hu ◽  
Guangpeng Zhang ◽  
...  
Keyword(s):  
Knowledge Bases ◽  
Named Entity ◽  
Entity Discovery

scholarly journals Linking chemical and disease entities to ontologies by integrating PageRank with extracted relations from literature

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
Pedro Ruas ◽  
Andre Lamurias ◽  
Francisco M. Couto
Keyword(s):  
Digital Libraries ◽  
Information Overload ◽  
Relation Extraction ◽  
Knowledge Bases ◽  
Entity Linking ◽  
Personalized Pagerank ◽  
Named Entity ◽  
Manual Curation ◽  
Low Performance ◽  
Gold Standards

Abstract Background Named Entity Linking systems are a powerful aid to the manual curation of digital libraries, which is getting increasingly costly and inefficient due to the information overload. Models based on the Personalized PageRank (PPR) algorithm are one of the state-of-the-art approaches, but these have low performance when the disambiguation graphs are sparse. Findings This work proposes a Named Entity Linking framework designated by Relation Extraction for Entity Linking (REEL) that uses automatically extracted relations to overcome this limitation. Our method builds a disambiguation graph, where the nodes are the ontology candidates for the entities and the edges are added according to the relations established in the text, which the method extracts automatically. The PPR algorithm and the information content of each ontology are then applied to choose the candidate for each entity that maximises the coherence of the disambiguation graph. We evaluated the method on three gold standards: the subset of the CRAFT corpus with ChEBI annotations (CRAFT-ChEBI), the subset of the BC5CDR corpus with disease annotations from the MEDIC vocabulary (BC5CDR-Diseases) and the subset with chemical annotations from the CTD-Chemical vocabulary (BC5CDR-Chemicals). The F1-Score achieved by REEL was 85.8%, 80.9% and 90.3% in these gold standards, respectively, outperforming baseline approaches. Conclusions We demonstrated that RE tools can improve Named Entity Linking by capturing semantic information expressed in text missing in Knowledge Bases and use it to improve the disambiguation graph of Named Entity Linking models. REEL can be adapted to any text mining pipeline and potentially to any domain, as long as there is an ontology or other knowledge Base available.

scholarly journals Improving Biomedical Named Entity Recognition with Label Re-correction and Knowledge Distillation

2020 ◽  
Author(s):  
Huiwei Zhou ◽  
Zhe Liu ◽  
Chengkun Lang ◽  
Yingyu Lin ◽  
Junjie Hou
Keyword(s):  
High Performance ◽  
Named Entity Recognition ◽  
Knowledge Bases ◽  
Entity Recognition ◽  
High Quality ◽  
Named Entity ◽  
Iterative Correction ◽  
Comparison Results ◽  
Knowledge Distillation ◽  
Biomedical Named Entity Recognition

Abstract Background: Biomedical named entities recognition is one of the most essential tasks in biomedical information extraction. Previous studies suffer from inadequate annotation datasets, especially the limited knowledge contained in them. Methods: To remedy the above issue, we propose a novel Chemical and Disease Named Entity Recognition (CDNER) framework with label re-correction and knowledge distillation strategies, which could not only create large and high-quality datasets but also obtain a high-performance entity recognition model. Our framework is inspired by two points: 1) named entity recognition should be considered from the perspective of both coverage and accuracy; 2) trustable annotations should be yielded by iterative correction. Firstly, for coverage, we annotate chemical and disease entities in a large unlabeled dataset by PubTator to generate a weakly labeled dataset. For accuracy, we then filter it by utilizing multiple knowledge bases to generate another dataset. Next, the two datasets are revised by a label re-correction strategy to construct two high-quality datasets, which are used to train two CDNER models, respectively. Finally, we compress the knowledge in the two models into a single model with knowledge distillation. Results: Experiments on the BioCreative V chemical-disease relation corpus show that knowledge from large datasets significantly improves CDNER performance, leading to new state-of-the-art results.Conclusions: We propose a framework with label re-correction and knowledge distillation strategies. Comparison results show that the two perspectives of knowledge in the two re-corrected datasets respectively are complementary and both effective for biomedical named entity recognition.

Exploiting Linked Data for Open and Configurable Named Entity Extraction

2015 ◽  
Vol 24 (02) ◽  
pp. 1540012 ◽  
Author(s):  
Pavlos Fafalios ◽  
Manolis Baritakis ◽  
Yannis Tzitzikas
Keyword(s):  
Linked Data ◽  
Question Answering ◽  
Knowledge Bases ◽  
Semantic Knowledge ◽  
Configuration Model ◽  
Generic Model ◽  
Entity Extraction ◽  
Named Entity ◽  
Domain Specific ◽  
Named Entity Extraction

Named Entity Extraction (NEE) is the process of identifying entities in texts and, very commonly, linking them to related (Web) resources. This task is useful in several applications, e.g. for question answering, annotating documents, post-processing of search results, etc. However, existing NEE tools lack an open or easy configuration although this is very important for building domain-specific applications. For example, supporting a new category of entities, or specifying how to link the detected entities with online resources, is either impossible or very laborious. In this paper, we show how we can exploit semantic information (Linked Data) at real-time for configuring (handily) a NEE system and we propose a generic model for configuring such services. To explicitly define the semantics of the proposed model, we introduce an RDF/S vocabulary, called “Open NEE Configuration Model”, which allows a NEE service to describe (and publish as Linked Data) its entity mining capabilities, but also to be dynamically configured. To allow relating the output of a NEE process with an applied configuration, we propose an extension of the Open Annotation Data Model which also enables an application to run advanced queries over the annotated data. As a proof of concept, we present X-Link, a fully-configurable NEE framework that realizes this approach. Contrary to the existing tools, X-Link allows the user to easily define the categories of entities that are interesting for the application at hand by exploiting one or more semantic Knowledge Bases. The user is also able to update a category and specify how to semantically link and enrich the identified entities. This enhanced configurability allows X-Link to be easily configured for different contexts for building domain-specific applications. To test the approach, we conducted a task-based evaluation with users that demonstrates its usability, and a case study that demonstrates its feasibility.

scholarly journals Improving the recall of biomedical named entity recognition with label re-correction and knowledge distillation

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Huiwei Zhou ◽  
Zhe Liu ◽  
Chengkun Lang ◽  
Yibin Xu ◽  
Yingyu Lin ◽  
...  
Keyword(s):  
Large Scale ◽  
Named Entity Recognition ◽  
Knowledge Bases ◽  
Entity Recognition ◽  
High Quality ◽  
Recognition Model ◽  
Named Entity ◽  
Comparison Results ◽  
Knowledge Distillation ◽  
Biomedical Named Entity Recognition

Abstract Background Biomedical named entity recognition is one of the most essential tasks in biomedical information extraction. Previous studies suffer from inadequate annotated datasets, especially the limited knowledge contained in them. Methods To remedy the above issue, we propose a novel Biomedical Named Entity Recognition (BioNER) framework with label re-correction and knowledge distillation strategies, which could not only create large and high-quality datasets but also obtain a high-performance recognition model. Our framework is inspired by two points: (1) named entity recognition should be considered from the perspective of both coverage and accuracy; (2) trustable annotations should be yielded by iterative correction. Firstly, for coverage, we annotate chemical and disease entities in a large-scale unlabeled dataset by PubTator to generate a weakly labeled dataset. For accuracy, we then filter it by utilizing multiple knowledge bases to generate another weakly labeled dataset. Next, the two datasets are revised by a label re-correction strategy to construct two high-quality datasets, which are used to train two recognition models, respectively. Finally, we compress the knowledge in the two models into a single recognition model with knowledge distillation. Results Experiments on the BioCreative V chemical-disease relation corpus and NCBI Disease corpus show that knowledge from large-scale datasets significantly improves the performance of BioNER, especially the recall of it, leading to new state-of-the-art results. Conclusions We propose a framework with label re-correction and knowledge distillation strategies. Comparison results show that the two perspectives of knowledge in the two re-corrected datasets respectively are complementary and both effective for BioNER.

scholarly journals Context-aware multi-token concept recognition of biological entities

2021 ◽  
Vol 22 (S11) ◽  
Author(s):  
Kwangmin Kim ◽  
Doheon Lee
Keyword(s):  
Language Processing ◽  
Contextual Information ◽  
Named Entity Recognition ◽  
Knowledge Bases ◽  
Entity Recognition ◽  
Biological Knowledge ◽  
Concept Recognition ◽  
Named Entity ◽  
Named Entity Normalization ◽  
Biological Entities

Abstract Background Concept recognition is a term that corresponds to the two sequential steps of named entity recognition and named entity normalization, and plays an essential role in the field of bioinformatics. However, the conventional dictionary-based methods did not sufficiently addressed the variation of the concepts in actual use in literature, resulting in the particularly degraded performances in recognition of multi-token concepts. Results In this paper, we propose a concept recognition method of multi-token biological entities using neural models combined with literature contexts. The key aspect of our method is utilizing the contextual information from the biological knowledge-bases for concept normalization, which is followed by named entity recognition procedure. The model showed improved performances over conventional methods, particularly for multi-token concepts with higher variations. Conclusions We expect that our model can be utilized for effective concept recognition and variety of natural language processing tasks on bioinformatics.

scholarly journals An Automatically Generated Annotated Corpus for Albanian Named Entity Recognition

2018 ◽  
Vol 18 (1) ◽  
pp. 95-108 ◽  
Author(s):  
Klesti Hoxha ◽  
Artur Baxhaku
Keyword(s):  
News Media ◽  
Named Entity Recognition ◽  
Automatic Generation ◽  
Knowledge Bases ◽  
Entity Recognition ◽  
High Demand ◽  
Training Corpus ◽  
Named Entity ◽  
Retrieval Systems ◽  
Information Retrieval Systems

Abstract Named Entity Recognition (NER) is an important task in many NLP pipelines. It has become especially important for knowledge bases that power many of the nowadays information retrieval systems. In order to cope with the high demand for annotated training corpora for supervised NER systems, automatic generation approaches have been proposed. In this paper we report on the first automatically generated NE annotated corpus for Albanian. News articles from Albanian news media were used as a document source. They were automatically tagged using a custom generated gazetteer from the Albanian Wikipedia. Our evaluation results show that this corpus can be used as a baseline corpus for human annotated ones or as a training corpus where no other is available.

Sign in / Sign up

Export Citation Format

Share Document