scholarly journals Semantic Deep Learning: Prior Knowledge and a Type of Four-Term Embedding Analogy to Acquire Treatments for Well-Known Diseases (Preprint)

2019 ◽  
Author(s):  
Mercedes Arguello Casteleiro ◽  
Julio Des Diz ◽  
Nava Maroto ◽  
Maria Jesus Fernandez Prieto ◽  
Simon Peters ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Analogical Reasoning ◽  
Evidence Based ◽  
Semantic Field ◽  
Search Query ◽  
Disease Treatment ◽  
Search Queries ◽  
Semantic Fields ◽  
N Gram

BACKGROUND How to treat a disease remains to be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings from deep learning (embedding analogies) may extract such biomedical facts, although the state-of-the-art focuses on pair-based proportional (pairwise) analogies such as man:woman::king:queen (“<i>queen = −man +king +woman</i>”). OBJECTIVE This study aimed to systematically extract disease treatment statements with a Semantic Deep Learning (SemDeep) approach underpinned by prior knowledge and another type of 4-term analogy (other than pairwise). METHODS As preliminaries, we investigated Continuous Bag-of-Words (CBOW) embedding analogies in a common-English corpus with five lines of text and observed a type of 4-term analogy (not pairwise) applying the 3CosAdd formula and relating the semantic fields <i>person</i> and <i>death</i>: “dagger = −Romeo +die +died” (search query: −<i>Romeo +die +died</i>). Our SemDeep approach worked with pre-existing items of knowledge (what is known) to make inferences sanctioned by a 4-term analogy (search query −<i>x +z1 +z2</i>) from CBOW and Skip-gram embeddings created with a PubMed systematic reviews subset (PMSB dataset). Stage1: Knowledge acquisition. Obtaining a set of terms, candidate y, from embeddings using vector arithmetic. Some n-gram pairs from the cosine and validated with evidence (prior knowledge) are the input for the 3cosAdd, seeking a type of 4-term analogy relating the semantic fields disease and treatment. Stage 2: Knowledge organization. Identification of candidates sanctioned by the analogy belonging to the semantic field treatment and mapping these candidates to unified medical language system Metathesaurus concepts with MetaMap. A concept pair is a brief disease treatment statement (biomedical fact). Stage 3: Knowledge validation. An evidence-based evaluation followed by human validation of biomedical facts potentially useful for clinicians. RESULTS We obtained 5352 n-gram pairs from 446 search queries by applying the 3CosAdd. The microaveraging performance of MetaMap for candidate <i>y</i> belonging to the semantic field <i>treatment</i> was F-measure=80.00% (precision=77.00%, recall=83.25%). We developed an empirical heuristic with some predictive power for <i>clinical winners</i>, that is, search queries bringing candidate <i>y</i> with evidence of a therapeutic intent for target disease <i>x</i>. The search queries <i>-asthma +inhaled_corticosteroids +inhaled_corticosteroid</i> and <i>-epilepsy +valproate +antiepileptic_drug</i> were <i>clinical winners</i>, finding eight evidence-based beneficial treatments. CONCLUSIONS Extracting treatments with therapeutic intent by analogical reasoning from embeddings (423K n-grams from the PMSB dataset) is an ambitious goal. Our SemDeep approach is knowledge-based, underpinned by embedding analogies that exploit prior knowledge. Biomedical facts from embedding analogies (4-term type, not pairwise) are potentially useful for clinicians. The heuristic offers a practical way to discover beneficial treatments for well-known diseases. Learning from deep learning models does not require a massive amount of data. Embedding analogies are not limited to pairwise analogies; hence, analogical reasoning with embeddings is underexploited.

scholarly journals Semantic Deep Learning: Prior Knowledge and a Type of Four-Term Embedding Analogy to Acquire Treatments for Well-Known Diseases

10.2196/16948 ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. e16948
Author(s):  
Mercedes Arguello Casteleiro ◽  
Julio Des Diz ◽  
Nava Maroto ◽  
Maria Jesus Fernandez Prieto ◽  
Simon Peters ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Analogical Reasoning ◽  
Evidence Based ◽  
Semantic Field ◽  
Search Query ◽  
Disease Treatment ◽  
Search Queries ◽  
Semantic Fields ◽  
N Gram

Background How to treat a disease remains to be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings from deep learning (embedding analogies) may extract such biomedical facts, although the state-of-the-art focuses on pair-based proportional (pairwise) analogies such as man:woman::king:queen (“queen = −man +king +woman”). Objective This study aimed to systematically extract disease treatment statements with a Semantic Deep Learning (SemDeep) approach underpinned by prior knowledge and another type of 4-term analogy (other than pairwise). Methods As preliminaries, we investigated Continuous Bag-of-Words (CBOW) embedding analogies in a common-English corpus with five lines of text and observed a type of 4-term analogy (not pairwise) applying the 3CosAdd formula and relating the semantic fields person and death: “dagger = −Romeo +die +died” (search query: −Romeo +die +died). Our SemDeep approach worked with pre-existing items of knowledge (what is known) to make inferences sanctioned by a 4-term analogy (search query −x +z1 +z2) from CBOW and Skip-gram embeddings created with a PubMed systematic reviews subset (PMSB dataset). Stage1: Knowledge acquisition. Obtaining a set of terms, candidate y, from embeddings using vector arithmetic. Some n-gram pairs from the cosine and validated with evidence (prior knowledge) are the input for the 3cosAdd, seeking a type of 4-term analogy relating the semantic fields disease and treatment. Stage 2: Knowledge organization. Identification of candidates sanctioned by the analogy belonging to the semantic field treatment and mapping these candidates to unified medical language system Metathesaurus concepts with MetaMap. A concept pair is a brief disease treatment statement (biomedical fact). Stage 3: Knowledge validation. An evidence-based evaluation followed by human validation of biomedical facts potentially useful for clinicians. Results We obtained 5352 n-gram pairs from 446 search queries by applying the 3CosAdd. The microaveraging performance of MetaMap for candidate y belonging to the semantic field treatment was F-measure=80.00% (precision=77.00%, recall=83.25%). We developed an empirical heuristic with some predictive power for clinical winners, that is, search queries bringing candidate y with evidence of a therapeutic intent for target disease x. The search queries -asthma +inhaled_corticosteroids +inhaled_corticosteroid and -epilepsy +valproate +antiepileptic_drug were clinical winners, finding eight evidence-based beneficial treatments. Conclusions Extracting treatments with therapeutic intent by analogical reasoning from embeddings (423K n-grams from the PMSB dataset) is an ambitious goal. Our SemDeep approach is knowledge-based, underpinned by embedding analogies that exploit prior knowledge. Biomedical facts from embedding analogies (4-term type, not pairwise) are potentially useful for clinicians. The heuristic offers a practical way to discover beneficial treatments for well-known diseases. Learning from deep learning models does not require a massive amount of data. Embedding analogies are not limited to pairwise analogies; hence, analogical reasoning with embeddings is underexploited.

INTERPRETATIONAL FIELD OF THE CONCEPT “WOMAN” IN ENGLISH AND KYRGYZ LINGUOCULTURES

2019 ◽  
pp. 54-56
Author(s):  
Баяманова М.С.
Keyword(s):  
Comparative Study ◽  
Key Words ◽  
Analytical Data ◽  
Semantic Field ◽  
Traditional Values ◽  
Lexical Unit ◽  
Semantic Fields ◽  
Field Culture

Summary: The article deals with the analysis of the interpretational field of the basic lexical units which represent the meaning of the concept “woman” in English and Kyrgyz languages and cultures. Comparative – contrastive analytical data of the most frequently used in both languages variants of the interpretation of the concept “woman” have been given. The semantic fields of nuclear and nearnuclear meanings of the lexical units, transforming the notion of “woman” in English and Kyrgyz languages and also the place and role of these notions in cultures and philosophy of the nations on the basis of mentality and traditional values have been studied and described. The situations of the use of this or that variant of the meaning of lexical unit. A comparative study of the definitions of the word “woman’ in English and Kyrgyz languages have been given. Key words: concept, woman, interpretational field, notion, definition, semantic field, culture, language, linguoculture, transformation Аннотация: В статье рассматриваются интерпретационные поля основных лексических единиц, репрезентирующих значение концепта «женщина» в английской и кыргызской лингвокультурах. Приводятся сравнительно-сопоставительные аналитические данные наиболее употребительных в речи обоих языков вариантов интерпретации концепта «женщина». Изучены и описаны семантические поля ядерных и околоядерных значений лексических единиц, трансформирующих понятие «женщина» в английском и кыргызском языке, а также роль и место этих понятий в культурах и философии народов на основе менталитета и традиционных ценностей. Приводятся ситуации использования того или ино- го варианта значения лексической единицы, проведено сравнительное изучение определений слова «женщина» в английском и кыргызском языках. Ключевые слова: концепт, женщина, интерпретационное поле, понятие, определение, семантическое поле, культура, язык, лингвокультура, трансформация Аннотация: Макалада англис жана кыргыз тилдеринде жана маданияттарында «аял» концептинин маанисин репрезентациалаган негизги лексикалык бирдиктер каралат. «Аял» концептин эки тилдеги кѳп колдонулуучу интерпретациялоо варианттарынын аналитикалык салыштырма маалыматтары изил- делип берилген. Англис жана кыргыз тилдеринде «аял» түшүнүгүн трансформациялаган лексикалык бирдиктердин түп нуска жана ага жакындашкан маанилери иликтелип каралган. Берилген түшүнүктѳрдүн элдик философиясында жана маданиятында, менталитеттин жана салттын негизинде эл арасына кеӊири тараган, элдик тилде жана маданиятта ойногон ролу менен орду чагылдырылган. Ар түрдү ситацияларда колдонулуучу тиги же бул лексикалык бирдиктердин маанисинин варианттары каралган, «аял» деген сѳздун англис жана кыргыз тилдериндеги түшүндүрмѳлѳрү салыштырылып изилделген. Түйүндүү сѳздѳр: концепт, аял, интерпретациялоо мейкиндиги, түшүнүк, түшүндүрмѳ, семантикалык чѳйрѳ, маданият, тил, лингвомаданият, трансформациялоо

Correlation of Phraseological Semantic Fields in Russian Study of Aphorisms

2020 ◽  
pp. 60-71
Author(s):  
Anshelika Korolkova
Keyword(s):  
Negative Correlation ◽  
Semantic Field ◽  
Positive Correlation ◽  
Classical Study ◽  
Semantic Fields ◽  
Zero Correlation ◽  
Russian Study

The article deals with the interconnection and interdependence of phraseological semantic fields of Russian study of aphorisms in synchronic and in diachronic approaches. The correlation of phraseological semantic fields of Russian study of aphorisms is considered as their interdependence due to various factors (linguistic and extra-linguistic ones). The correlation of the phraseological semantic fields of Russian study of aphorisms is manifested in the existence of many antinomies. The natural linguistic antinomies of life / death / immortality or war / peace, or good / evil, or friend / enemy, or villainy / nobility are reflected in Russian aphorisms and have entered the corresponding phraseological semantic fields. The corpus of Russian study of aphorisms containsnot only antinomic aphorisms, but also antinomic relations that extend to the level of language and speech. Therefore, in Russian study of aphorisms there are phraseological semantic fields that implement these antinomies. In addition to the antinomic phraseological semantic fields in the corpus of classical Russian study of aphorisms there are other types of correlations. The keywords (concepts) of many phraseological semantic fields are closely thematically connected. When the number of units from one field is changed, the number of units in another phraseological semantic field also changes. Most phraseological semantic fields of Russian study of aphorisms do not show a zero correlation in either synchronic or diachronic approaches. This is due to, first of all, the universality of the aphoristic theme, with all the ideological and thematic uniqueness of the sayings used by Russian writers. However, a few phraseological and semantic fields of aphorisms by Russian writers may show a negative correlation, which is due to the diversity of the thematic groups that comprise them. A positive correlation of phraseological semantic fields, the most significant in the number of their constituent components, shows deep internal linguistic systemic connections in Russian classical study of aphorisms.

Parsing of Urban Facades from 3D Point Clouds Based on a Novel Multi-View Domain

2021 ◽  
Vol 87 (4) ◽  
pp. 283-293
Author(s):  
Wei Wang ◽  
Yuan Xu ◽  
Yingchao Ren ◽  
Gang Wang
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Performance Improvement ◽  
Data Distribution ◽  
Point Clouds ◽  
Learning Models ◽  
Data Set ◽  
3D Point Clouds ◽  
Segmentation Accuracy ◽  
The Mean

Recently, performance improvement in facade parsing from 3D point clouds has been brought about by designing more complex network structures, which cost huge computing resources and do not take full advantage of prior knowledge of facade structure. Instead, from the perspective of data distribution, we construct a new hierarchical mesh multi-view data domain based on the characteristics of facade objects to achieve fusion of deep-learning models and prior knowledge, thereby significantly improving segmentation accuracy. We comprehensively evaluate the current mainstream method on the RueMonge 2014 data set and demonstrate the superiority of our method. The mean intersection-over-union index on the facade-parsing task reached 76.41%, which is 2.75% higher than the current best result. In addition, through comparative experiments, the reasons for the performance improvement of the proposed method are further analyzed.

scholarly journals Clustering of Authors’ Texts of English Fiction in the Vector Space of Semantic Fields

2014 ◽  
Vol 14 (3) ◽  
pp. 25-36
Author(s):  
Bohdan Pavlyshenko
Keyword(s):  
Cluster Analysis ◽  
Vector Space ◽  
Cluster Structure ◽  
Vector Space Model ◽  
Semantic Space ◽  
Field Vector ◽  
Semantic Field ◽  
Text Documents ◽  
Space Model ◽  
Semantic Fields

Abstract This paper describes the analysis of possible differentiation of the author’s idiolect in the space of semantic fields; it also analyzes the clustering of text documents in the vector space of semantic fields and in the semantic space with orthogonal basis. The analysis showed that using the vector space model on the basis of semantic fields is efficient in cluster analysis algorithms of author’s texts in English fiction. The study of the distribution of authors' texts in the cluster structure showed the presence of the areas of semantic space that represent the idiolects of individual authors. Such areas are described by the clusters where only one author dominates. The clusters, where the texts of several authors dominate, can be considered as areas of semantic similarity of author’s styles. SVD factorization of the semantic fields matrix makes it possible to reduce significantly the dimension of the semantic space in the cluster analysis of author’s texts. Using the clustering of the semantic field vector space can be efficient in a comparative analysis of author's styles and idiolects. The clusters of some authors' idiolects are semantically invariant and do not depend on any changes in the basis of the semantic space and clustering method.

scholarly journals Case Study of Deep Learning Model of Temperature-Induced Deflection of a Cable-Stayed Bridge Driven by Data Knowledge

Symmetry ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2293
Author(s):  
Zixiang Yue ◽  
Youliang Ding ◽  
Hanwei Zhao ◽  
Zhiwen Wang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Prior Knowledge ◽  
Learning Model ◽  
Bridge Management ◽  
Learning Network ◽  
Cable Stayed Bridge ◽  
Main Girder ◽  
Deep Learning Model

A cable-stayed bridge is a typical symmetrical structure, and symmetry affects the deformation characteristics of such bridges. The main girder of a cable-stayed bridge will produce obvious deflection under the inducement of temperature. The regression model of temperature-induced deflection is hoped to provide a comparison value for bridge evaluation. Based on the temperature and deflection data obtained by the health monitoring system of a bridge, establishing the correlation model between temperature and temperature-induced deflection is meaningful. It is difficult to complete a high-quality model only by the girder temperature. The temperature features based on prior knowledge from the mechanical mechanism are used as the input information in this paper. At the same time, to strengthen the nonlinear ability of the model, this paper selects an independent recurrent neural network (IndRNN) for modeling. The deep learning neural network is compared with machine learning neural networks to prove the advancement of deep learning. When only the average temperature of the main girder is input, the calculation accuracy is not high regardless of whether the deep learning network or the machine learning network is used. When the temperature information extracted by the prior knowledge is input, the average error of IndRNN model is only 2.53%, less than those of BPNN model and traditional RNN. Combining knowledge with deep learning is undoubtedly the best modeling scheme. The deep learning model can provide a comparison value of bridge deformation for bridge management.

Challenge

2017 ◽  
pp. 10-25
Author(s):  
Lennie Scott-Webber
Keyword(s):  
Deep Learning ◽  
Learning Strategies ◽  
Teaching And Learning ◽  
Decision Makers ◽  
Evidence Based ◽  
Classroom Design ◽  
Left Behind ◽  
Current State ◽  
Behavioral Cues ◽  
Teaching And Learning Strategies

Too many stakeholders are ignoring too much scientific research and the net resulting outcome is too many students are left behind academically. Significant and strategic changes must occur quickly to correct this fundamental outcome. This chapter explores issues relative to the current state of classroom design and why they haven't changed systemically in over 4000 years. Definitions of active learning and behavioral research basics, the nature of the physical learning place, Evidence-Based Designs (EBD) solutions and examples of solution features and capabilities impacting pedagogy (i.e., teaching and learning strategies), technology and spaces are shared. Metrics of ‘proof' of engagement impact are cited, and this author argues that space provides behavioral cues. To simplify the complexity of moving from a teacher-centric paradigm and design solutions to a learner-centric one, two important items for consideration are presented: 1) a formula guiding deep learning parameters for all stakeholders and 2) a decision-makers' checklist.

Fake News Detection Using Deep Learning

2021 ◽  
pp. 440-451
Author(s):  
Varalakshmi Konagala ◽  
Shahana Bano
Keyword(s):  
Deep Learning ◽  
Uncertain Data ◽  
Online News ◽  
Sufficient Information ◽  
Fake News ◽  
Web Based ◽  
News Sources ◽  
N Gram

The engendering of uncertain data in ordinary access news sources, for example, news sites, web-based life channels, and online papers, have made it trying to recognize capable news sources, along these lines expanding the requirement for computational instruments ready to give into the unwavering quality of online substance. For instance, counterfeit news outlets were observed to be bound to utilize language that is abstract and enthusiastic. At the point when specialists are chipping away at building up an AI-based apparatus for identifying counterfeit news, there wasn't sufficient information to prepare their calculations; they did the main balanced thing. In this chapter, two novel datasets for the undertaking of phony news locations, covering distinctive news areas, distinguishing proof of phony substance in online news has been considered. N-gram model will distinguish phony substance consequently with an emphasis on phony audits and phony news. This was pursued by a lot of learning analyses to fabricate precise phony news identifiers and showed correctness of up to 80%.

Dynamic Query Intent Prediction from a Search Log Stream

2016 ◽  
Vol 6 (2) ◽  
pp. 66-85
Author(s):  
Wael K. Hanna ◽  
Aziza Saad Asem ◽  
M. B. Senousy
Keyword(s):  
Experimental Data ◽  
Search Engines ◽  
Evaluation Metrics ◽  
Search Query ◽  
Data Set ◽  
Query Log ◽  
Search Queries ◽  
Query Intent ◽  
Query Logs ◽  
Intent Prediction

The users that used search engines are obligated to express their goals in few words (queries). Sometimes search queries are ambiguous. Moreover, the users' intents are dynamically evolving. This paper analyzes the user's query logs to classify the related queries, the related intent topic categories and the related intent types and use this classification to dynamically predict the users' future queries, its intent topic and its intent type. AOL Search Query Log is taken as an experimental data set. Then use evaluation metrics to evaluate the prediction results.

Sign in / Sign up

Export Citation Format

Share Document