scholarly journals HYPHEN

Terminology ◽  
2018 ◽  
Vol 24 (1) ◽  
pp. 91-121 ◽  
Author(s):  
Paul Thompson ◽  
Sophia Ananiadou
Keyword(s):  
Word Order ◽  
Sources Of Information ◽  
Robust Performance ◽  
Surface Level ◽  
Domain Specific ◽  
Text Types ◽  
Word Forms ◽  
Locating Information ◽  
Clinical Records ◽  
Normalisation Method

Abstract Narrative clinical records and biomedical articles constitute rich sources of information about phenotypes, i.e., markers distinguishing individuals with specific medical conditions from the general population. Phenotypes help clinicians to provide personalised treatments. However, locating information about them within huge document repositories is difficult, since each phenotypic concept can be mentioned in many ways. Normalisation methods automatically map divergent phrases to unique concepts in domain-specific terminologies, to allow location and linking of all mentions of a concept of interest. We have developed a hybrid normalisation method (HYPHEN) to handle concept mentions with wide ranging characteristics, across different text types. HYPHEN integrates various normalisation techniques that handle surface-level variations (e.g., differences in word order, word forms or acronyms/abbreviations) and lexical-level variations (where terms have similar meanings, but potentially unrelated forms). HYPHEN achieves robust performance for both biomedical academic text and narrative clinical records, and has the ability to significantly outperform related methods.

scholarly journals MMoOn Core – the Multilingual Morpheme Ontology

Semantic Web ◽  
2020 ◽  
pp. 1-29
Author(s):  
Bettina Klimek ◽  
Markus Ackermann ◽  
Martin Brümmer ◽  
Sebastian Hellmann
Keyword(s):  
Semantic Web ◽  
Linked Data ◽  
Semantic Model ◽  
Lexical Resources ◽  
Domain Specific ◽  
Word Forms ◽  
Language Data ◽  
Core Ontology ◽  
Machine Readable ◽  
Rapid Emergence

In the last years a rapid emergence of lexical resources has evolved in the Semantic Web. Whereas most of the linguistic information is already machine-readable, we found that morphological information is mostly absent or only contained in semi-structured strings. An integration of morphemic data has not yet been undertaken due to the lack of existing domain-specific ontologies and explicit morphemic data. In this paper, we present the Multilingual Morpheme Ontology called MMoOn Core which can be regarded as the first comprehensive ontology for the linguistic domain of morphological language data. It will be described how crucial concepts like morphs, morphemes, word forms and meanings are represented and interrelated and how language-specific morpheme inventories can be created as a new possibility of morphological datasets. The aim of the MMoOn Core ontology is to serve as a shared semantic model for linguists and NLP researchers alike to enable the creation, conversion, exchange, reuse and enrichment of morphological language data across different data-dependent language sciences. Therefore, various use cases are illustrated to draw attention to the cross-disciplinary potential which can be realized with the MMoOn Core ontology in the context of the existing Linguistic Linked Data research landscape.

Morphological Means in Russian: Clarification of the Concept

2021 ◽  
Vol 20 (9) ◽  
pp. 23-33
Author(s):  
Galina I. Panova ◽  
Tatiana V. Viktorina ◽  
Antonina E. Kuzmina
Keyword(s):  
Word Order ◽  
Morphological Structure ◽  
Russian Language ◽  
Word Form ◽  
Similar Function ◽  
Word Forms ◽  
The Status ◽  
Definition Of ◽  
Linguistic Units ◽  
The Russian Language

The concept of “morphological / grammatical means” is widely used in studies on the Russian language, although there is no generally accepted interpretation. This work analyzes the reflection of this concept in Russian studies and clarifies the status of those linguistic units that are traditionally referred to as morphological means: form-building affixes, alternating sounds (internal inflection), stress, supplementary word stems, auxiliary words, intonation, as well as word order. Our research has shown that these linguistic units have different functional status in the morphological structure of the Russian language. First, these are categorical, or actually morphological, means, represented by formative affixes and auxiliary words. They are carriers of morphological meanings in the structure of abstracted morphological forms – the basic units of inflectional Russian morphology. Secondly, a non-categorical means, syncretic and accidental for morphology, are supplementary stems that contain not only lexical, but also morphological meaning and thus duplicate the expression of morphological information in a word form with a form-building affix. Thirdly, these are linguistic units that are not elements of the morphological structure, but have morphological significance, which is manifested in their ability to differentiate homonymous morphological forms in the structure of word forms (alternating sounds and stress) or utterances (intonation). Word order can also perform a similar function. The study allows us to clarify the definition of the concept under consideration: morphological means are linguistic units that are carriers of morphological meanings and constituents of morphological forms.

Do you investigate word order in detail or do you investigate in detail word order? On word order and headedness in the recent history of English

2016 ◽  
Vol 12 (1) ◽  
Author(s):  
Javier Pérez-Guerra
Keyword(s):  
Early Modern ◽  
Middle English ◽  
Word Order ◽  
Noun Phrases ◽  
Recent History ◽  
Verb Phrases ◽  
Text Types ◽  
History Of ◽  
Late Modern

AbstractThis paper examines the design of verb phrases and noun phrases, focusing on the diachronic tendencies observed in the data in Middle English, Early Modern, and Late Modern English. The approach is corpus-based and the data, representing different periods and text types, is taken from the

Children’s Self-Perceptions in the Physical Domain: Between- and Within-Age Variability in Level, Accuracy, and Sources of Perceived Competence

2005 ◽  
Vol 27 (2) ◽  
pp. 226-244 ◽  
Author(s):  
Maureen R. Weiss ◽  
Anthony J. Amorose
Keyword(s):  
Cluster Analysis ◽  
Age Differences ◽  
Information Sources ◽  
Perceived Competence ◽  
Physical Domain ◽  
Sources Of Information ◽  
Self Perception ◽  
Domain Specific ◽  
Self Perceptions ◽  
Self Reports

Both level (high vs. low) and accuracy (discrepancy between perceived and actual) of perceived competence are important contributors to domain-specific emotions and motivational processes. Moreover, age differences in level and accuracy of perceived competence have been explained by the sources of information children use to judge their competence. Thus the purpose of our study was to examine simultaneously the interrelationships among age, actual competence, and level, accuracy, and sources of perceived competence. Children (N = 159) completed self-reports while teachers rated their actual competence at a sport camp. Cluster analysis revealed five profiles of children who varied in age, actual competence, perceived competence, and accuracy of perceived competence. These groups were further distinguished by the importance they placed on competence information sources. Results indicate that age, actual ability, and level, accuracy, and sources of perceived competence should be considered simultaneously in research on self-perception and motivational processes among youth.

scholarly journals Quality of Life and Autonomy in Patients with Intermittent Bladder Catheterization Trained by Specialized Nurses

2021 ◽  
Vol 10 (17) ◽  
pp. 3909
Author(s):  
Blanca Fernandez-Lasquetty Blanc ◽  
Julián Rodríguez-Almagro ◽  
Carlos Lorenzo-García ◽  
Elena Alcaraz-Zomeño ◽  
Guadalupe Fernandez-Llorente ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Depression Scale ◽  
Anxiety And Depression ◽  
Prevention Measures ◽  
Sources Of Information ◽  
Paired Data ◽  
Bladder Catheterization ◽  
King’S Health Questionnaire ◽  
Clinical Records

Intermittent bladder catheterization (IBC) involves regular urine draining using a catheter, which is removed immediately after urinary elimination. It allows for the patient’s urological health to be managed and their renal function to be preserved, and it promotes autonomy. Compliance with the prescribed number of daily catheterizations, which must be conducted by the patient, and infection prevention measures are crucial. To identify the patients requiring IBC, and to determine their adherence (whether they followed the prescribed guidelines and their difficulty in carrying out the procedure, as well as to assess how the IBC influences their quality of life and state of mind after receiving self-care training from a specialized nurse), we carried out a prospective, multicenter observational study in 24 Spanish hospitals with one month of monitoring and a sample of 99 patients. The sources of information were the patients’ clinical records, the King’s Health Questionnaire, the Mini-Mental State Examination (MMSE), and the hospital anxiety and depression scale (HADS). Descriptive and bivariate statistics were used to analyses the paired data. After recruitment (n = 99), 79 patients completed the questionnaire at a mean age of 35.2 years (SD = 20.5 years). In total, 53.5% (53) of the sample consisted of men and 32.3% (32) had neurological damage as the reason for prescription; 67% (67.7) performed self-catheterization and 86.7% adhered to the IBC. After one month of monitoring, a statistically significant improvement in quality of life was observed in all criteria, with the exception of personal relationships (p < 0.005), as well as an improvement in anxiety and depression levels (p < 0.001). Patients who require IBC show good adherence to the IBC with a significant percentage of self-catheterization. After one month of IBC, a significant improvement in the patients’ quality of life and mood was observed. These results could be attributed to adequate patient training and adequate personalization of the IBC materials by the specialized nurses.

Automated Identification of Diagnosis and Co-morbidity in Clinical Records

2009 ◽  
Vol 48 (06) ◽  
pp. 546-551 ◽  
Author(s):  
C. Cano ◽  
A. Blanco ◽  
L. Peshkin
Keyword(s):  
Rapid Prototyping ◽  
Computational Linguistics ◽  
High Performance ◽  
Ad Hoc ◽  
Expert Knowledge ◽  
Free Text ◽  
Automated Identification ◽  
Domain Specific ◽  
Co Morbidity ◽  
Clinical Records

Summary Objectives: Automated understanding of clinical records is a challenging task involving various legal and technical difficulties. Clinical free text is inherently redundant, unstructured, and full of acronyms, abbreviations and domain-specific language which make it challenging to mine automatically. There is much effort in the field focused on creating specialized ontology, lexicons and heuristics based on expert knowledge of the domain. However, ad-hoc solutions poorly generalize across diseases or diagnoses. This paper presents a successful approach for a rapid prototyping of a diagnosis classifier based on a popular computational linguistics platform. Methods: The corpus consists of several hundred of full length discharge summaries provided by Partners Healthcare. The goal is to identify a diagnosis and assign co-morbidity. Our approach is based on the rapid implementation of a logistic regression classifier using an existing toolkit: LingPipe (http://alias-i.com/lingpipe). We implement and compare three different classifiers. The baseline approach uses character 5-grams as features. The second approach uses a bag-of-words representation enriched with a small additional set of features. The third approach reduces a feature set to the most informative features according to the information content. Results: The proposed systems achieve high performance (average F-micro 0.92) for the task. We discuss the relative merit of the three classifiers. Supplementary material with detailed results is available at: http://decsai.ugr.es/~ccano/LR/supplementary_material/ Conclusions: We show that our methodology for rapid prototyping of a domain-unaware system is effective for building an accurate classifier for clinical records.

Data Science and Computational Biology

Biotechnology ◽  
2019 ◽  
pp. 1277-1292
Author(s):  
Singaraju Jyothi ◽  
Bhargavi P
Keyword(s):  
Computational Biology ◽  
High Performance ◽  
Data Science ◽  
Personalised Medicine ◽  
Big Data Analytics ◽  
Biological Data ◽  
Domain Specific ◽  
Data Volume ◽  
Domain Specific Knowledge ◽  
Clinical Records

Data Science and Computational biology is an interdisciplinary program that brings together the domain specific knowledge of science and engineering with relevant areas of computing and bioinformatics. Data science has the potential to revolutionise healthcare, and respond to the increasing volume and complexity in biomedical and bioinformatics data. From genomics to clinical records, from imaging to mobile health and personalised medicine, the data volume in biomedical research presents urgent challenges for computer science. This chapter elevates the researchers in what way data science play important role in Computational Biology such as Bio-molecular Computation, Computational Photonics, Medical Imaging, Scientific Computing, Structural Biology, Bioinformatics and Bio-Computing etc. Big data analytics of biological data bases, high performance computing in large sequence of genome database and Scientific Visualization are also discussed in this chapter.

Retrieving Domain-Specific Collocations by Co-occurrences and Word Order Constraints

1999 ◽  
Vol 15 (2) ◽  
pp. 92-100 ◽  
Author(s):  
Sayori Shimohata ◽  
Toshiyuki Sugio ◽  
Junji Nagata
Keyword(s):  
Word Order ◽  
Domain Specific ◽  
Order Constraints

Sentiment analysis in Turkish: Supervised, semi-supervised, and unsupervised techniques

2020 ◽  
pp. 1-29
Author(s):  
Cem Rıfkı Aydın ◽  
Tunga Güngör
Keyword(s):  
Sentiment Analysis ◽  
Morphological Analysis ◽  
State Of The Art ◽  
Feature Weighting ◽  
Domain Specific ◽  
Word Forms ◽  
Supervised Classifiers ◽  
Supervised Methods ◽  
Domain Independent ◽  
Agglutinative Language

Abstract Although many studies on sentiment analysis have been carried out for widely spoken languages, this topic is still immature for Turkish. Most of the works in this language focus on supervised models, which necessitate comprehensive annotated corpora. There are a few unsupervised methods, and they utilize sentiment lexicons either built by translating from English lexicons or created based on corpora. This results in improper word polarities as the language and domain characteristics are ignored. In this paper, we develop unsupervised (domain-independent) and semi-supervised (domain-specific) methods for Turkish, which are based on a set of antonym word pairs as seeds. We make a comprehensive analysis of supervised methods under several feature weighting schemes. We then form ensemble of supervised classifiers and also combine the unsupervised and supervised methods. Since Turkish is an agglutinative language, we perform morphological analysis and use different word forms. The methods developed were tested on two datasets having different styles in Turkish and also on datasets in English to show the portability of the approaches across languages. We observed that the combination of the unsupervised and supervised approaches outperforms the other methods, and we obtained a significant improvement over the state-of-the-art results for both Turkish and English.

Sign in / Sign up

Export Citation Format

Share Document