Knowledge Acquisition Through Ontologies from Medical Natural Language Texts

2017 ◽  
Vol 10 (4) ◽  
pp. 56-69 ◽  
Author(s):  
José Medina-Moreira ◽  
Katty Lagos-Ortiz ◽  
Harry Luna-Aveiga ◽  
Oscar Apolinario-Arzube ◽  
María del Pilar Salas-Zárate ◽  
...  
Keyword(s):  
Life Cycle ◽  
General Solution ◽  
Natural Language ◽  
The Other ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Clinical Knowledge ◽  
Biomedical Ontologies ◽  
Biomedical Field ◽  
F Measure

Ontologies are used to represent knowledge and they have become very important in the Semantic Web era. Ontologies evolve continuously during their life cycle to adapt to new requirements and needs, especially in the biomedical field, where the number of ontologies and their complexity have increased during the last years. On the other hand, a vast amount of clinical knowledge resides in natural language texts. For these reasons, building and maintaining biomedical ontologies from natural language texts is a relevant and challenging issue. In order to provide a general solution and to minimize the experts' participation during the ontology enriching process, a methodology for extracting terms and relations from natural language texts is proposed in this work. This framework is based on linguistic and statistical methods and semantic role labeling technologies, having been validated in the domain of diabetes, where they have obtained encouraging results with an F-measure of 82.1% and 79.9% for concepts and relations, respectively.

Knowledge Acquisition Through Ontologies from Medical Natural Language Texts

2020 ◽  
pp. 1023-1037
Author(s):  
José Medina-Moreira ◽  
Katty Lagos-Ortiz ◽  
Harry Luna-Aveiga ◽  
Oscar Apolinario-Arzube ◽  
María del Pilar Salas-Zárate ◽  
...  
Keyword(s):  
Life Cycle ◽  
General Solution ◽  
Semantic Web ◽  
Natural Language ◽  
Statistical Methods ◽  
The Other ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Biomedical Field ◽  
F Measure

Ontologies are used to represent knowledge and they have become very important in the Semantic Web era. Ontologies evolve continuously during their life cycle to adapt to new requirements and needs, especially in the biomedical field, where the number of ontologies and their complexity have increased during the last years. On the other hand, a vast amount of clinical knowledge resides in natural language texts. For these reasons, building and maintaining biomedical ontologies from natural language texts is a relevant and challenging issue. In order to provide a general solution and to minimize the experts' participation during the ontology enriching process, a methodology for extracting terms and relations from natural language texts is proposed in this work. This framework is based on linguistic and statistical methods and semantic role labeling technologies, having been validated in the domain of diabetes, where they have obtained encouraging results with an F-measure of 82.1% and 79.9% for concepts and relations, respectively.

scholarly journals Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

2021 ◽  
Author(s):  
Rexhina Blloshmi ◽  
Simone Conia ◽  
Rocco Tripodi ◽  
Roberto Navigli
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Great Success ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Complex Predicate ◽  
Input Sentence ◽  
End To End

Despite the recent great success of the sequence-to-sequence paradigm in Natural Language Processing, the majority of current studies in Semantic Role Labeling (SRL) still frame the problem as a sequence labeling task. In this paper we go against the flow and propose GSRL (Generating Senses and RoLes), the first sequence-to-sequence model for end-to-end SRL. Our approach benefits from recently-proposed decoder-side pretraining techniques to generate both sense and role labels for all the predicates in an input sentence at once, in an end-to-end fashion. Evaluated on standard gold benchmarks, GSRL achieves state-of-the-art results in both dependency- and span-based English SRL, proving empirically that our simple generation-based model can learn to produce complex predicate-argument structures. Finally, we propose a framework for evaluating the robustness of an SRL model in a variety of synthetic low-resource scenarios which can aid human annotators in the creation of better, more diverse, and more challenging gold datasets. We release GSRL at github.com/SapienzaNLP/gsrl.

scholarly journals Corpora Annotated with Negation: An Overview

2020 ◽  
Vol 46 (1) ◽  
pp. 1-52
Author(s):  
Salud María Jiménez-Zafra ◽  
Roser Morante ◽  
María Teresa Martín-Valdivia ◽  
L. Alfonso Ureña-López
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
The Internet ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Annotation Scheme ◽  
Linguistic Phenomenon ◽  
The Way

Negation is a universal linguistic phenomenon with a great qualitative impact on natural language processing applications. The availability of corpora annotated with negation is essential to training negation processing systems. Currently, most corpora have been annotated for English, but the presence of languages other than English on the Internet, such as Chinese or Spanish, is greater every day. In this study, we present a review of the corpora annotated with negation information in several languages with the goal of evaluating what aspects of negation have been annotated and how compatible the corpora are. We conclude that it is very difficult to merge the existing corpora because we found differences in the annotation schemes used, and most importantly, in the annotation guidelines: the way in which each corpus was tokenized and the negation elements that have been annotated. Differently than for other well established tasks like semantic role labeling or parsing, for negation there is no standard annotation scheme nor guidelines, which hampers progress in its treatment.

scholarly journals Domain adaptation for semantic role labeling of clinical text

2015 ◽  
Vol 22 (5) ◽  
pp. 967-979 ◽  
Author(s):  
Yaoyun Zhang ◽  
Buzhou Tang ◽  
Min Jiang ◽  
Jingqi Wang ◽  
Hua Xu
Keyword(s):  
Domain Adaptation ◽  
Biomedical Literature ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Clinical Text ◽  
Source Domain ◽  
Training Samples ◽  
Annotation Costs ◽  
Feature Augmentation ◽  
F Measure

Abstract Objective Semantic role labeling (SRL), which extracts a shallow semantic relation representation from different surface textual forms of free text sentences, is important for understanding natural language. Few studies in SRL have been conducted in the medical domain, primarily due to lack of annotated clinical SRL corpora, which are time-consuming and costly to build. The goal of this study is to investigate domain adaptation techniques for clinical SRL leveraging resources built from newswire and biomedical literature to improve performance and save annotation costs. Materials and Methods Multisource Integrated Platform for Answering Clinical Questions (MiPACQ), a manually annotated SRL clinical corpus, was used as the target domain dataset. PropBank and NomBank from newswire and BioProp from biomedical literature were used as source domain datasets. Three state-of-the-art domain adaptation algorithms were employed: instance pruning, transfer self-training, and feature augmentation. The SRL performance using different domain adaptation algorithms was evaluated by using 10-fold cross-validation on the MiPACQ corpus. Learning curves for the different methods were generated to assess the effect of sample size. Results and Conclusion When all three source domain corpora were used, the feature augmentation algorithm achieved statistically significant higher F-measure (83.18%), compared to the baseline with MiPACQ dataset alone (F-measure, 81.53%), indicating that domain adaptation algorithms may improve SRL performance on clinical text. To achieve a comparable performance to the baseline method that used 90% of MiPACQ training samples, the feature augmentation algorithm required <50% of training samples in MiPACQ, demonstrating that annotation costs of clinical SRL can be reduced significantly by leveraging existing SRL resources from other domains.

scholarly journals A Methodology for Ontology Reuse

2019 ◽  
Vol 15 (4) ◽  
pp. 1-21
Author(s):  
Nur Zareen Zulkarnain ◽  
Farid Meziane
Keyword(s):  
Abdominal Ultrasound ◽  
The Other ◽  
Biomedical Ontologies ◽  
Step Method ◽  
Additional Time ◽  
Domain Experts ◽  
Domain Specific ◽  
Biomedical Field ◽  
Ontology Reuse ◽  
Systematized Nomenclature Of Medicine

There is an abundance of existing biomedical ontologies such as the National Cancer Institute Thesaurus and the Systematized Nomenclature of Medicine-Clinical Terms. Implementing these ontologies in a particular system however, may cause unnecessary high usage of memory and slows down the systems' performance. On the other hand, building a new ontology from scratch will require additional time and efforts. Therefore, this research explores the ontology reuse approach in order to develop an Abdominal Ultrasound Ontology by extracting concepts from existing biomedical ontologies. This article presents the reader with a step by step method in reusing ontologies together with suggestions of the off-the-shelf tools that can be used to ease the process. The results show that ontology reuse is beneficial especially in the biomedical field as it allows for developers from the non-technical background to build and use domain specific ontology with ease. It also allows for developers with technical background to develop ontologies with minimal involvements from domain experts.

scholarly journals Applying Semantic Role Labeling and Spreading Activation Techniques for Semantic Information Retrieval

2020 ◽  
Vol 49 (2) ◽  
pp. 275-288
Author(s):  
Tomas Vileiniskis ◽  
Rita Butkiene
Keyword(s):  
Information Retrieval ◽  
Natural Language ◽  
Information Needs ◽  
Semantic Search ◽  
Spreading Activation ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Search Field ◽  
Semantically Enhanced ◽  
Spreading Activation Algorithm

Semantically enhanced information retrieval (IR) is aimed at improving classical IR methods and goes way beyond plain Boolean keyword matching with the main goal of better serving implicit and ambiguous information needs. As a de-facto pre-requisite to semantic IR, different information extraction (IE) techniques are used to mine unstructured text for underlying knowledge.  In this paper we present a method that combines both IE and IR to enable semantic search in natural language texts. First, we apply semantic role labeling (SRL) to automatically extract event-oriented information found in natural language texts to an RDF knowledge graph leveraging semantic web technology. Second, we investigate how a custom flavored graph traversal spreading activation algorithm can be employed to interpret user’s information needs on top of the prior-extracted knowledge base. Finally, we present an assessment on the applicability of our method for semantically enhanced IR. An experimental evaluation on partial WikiQA dataset shows the strengths of our approach and also unveils common pitfalls that we use as guidelines to draw further work directions in the open-domain semantic search field.

Sign in / Sign up

Export Citation Format

Share Document