scholarly journals A Novel Active Learning Regression Framework for Balancing the Exploration-Exploitation Trade-Off

Entropy ◽  
2019 ◽  
Vol 21 (7) ◽  
pp. 651 ◽  
Author(s):  
Dina Elreedy ◽  
Amir F. Atiya ◽  
Samir I. Shaheen
Keyword(s):  
Active Learning ◽  
Language Processing ◽  
Optimization Problems ◽  
Model Accuracy ◽  
Trade Off ◽  
Learning Framework ◽  
Domain Specific ◽  
Significant Performance ◽  
Price Demand ◽  
Exploration Exploitation

Recently, active learning is considered a promising approach for data acquisition due to the significant cost of the data labeling process in many real world applications, such as natural language processing and image processing. Most active learning methods are merely designed to enhance the learning model accuracy. However, the model accuracy may not be the primary goal and there could be other domain-specific objectives to be optimized. In this work, we develop a novel active learning framework that aims to solve a general class of optimization problems. The proposed framework mainly targets the optimization problems exposed to the exploration-exploitation trade-off. The active learning framework is comprehensive, it includes exploration-based, exploitation-based and balancing strategies that seek to achieve the balance between exploration and exploitation. The paper mainly considers regression tasks, as they are under-researched in the active learning field compared to classification tasks. Furthermore, in this work, we investigate the different active querying approaches—pool-based and the query synthesis—and compare them. We apply the proposed framework to the problem of learning the price-demand function, an application that is important in optimal product pricing and dynamic (or time-varying) pricing. In our experiments, we provide a comparative study including the proposed framework strategies and some other baselines. The accomplished results demonstrate a significant performance for the proposed methods.

scholarly journals Active learning: a step towards automating medical concept extraction

2015 ◽  
Vol 23 (2) ◽  
pp. 289-296 ◽  
Author(s):  
Mahnoosh Kholghi ◽  
Laurianne Sitbon ◽  
Guido Zuccon ◽  
Anthony Nguyen
Keyword(s):  
Active Learning ◽  
Language Processing ◽  
Selection Criteria ◽  
Conditional Random Fields ◽  
Free Text ◽  
Data Sets ◽  
Comparative Performance ◽  
Concept Extraction ◽  
Learning Framework ◽  
Medical Concept

Abstract Objective This paper presents an automatic, active learning-based system for the extraction of medical concepts from clinical free-text reports. Specifically, (1) the contribution of active learning in reducing the annotation effort and (2) the robustness of incremental active learning framework across different selection criteria and data sets are determined. Materials and methods The comparative performance of an active learning framework and a fully supervised approach were investigated to study how active learning reduces the annotation effort while achieving the same effectiveness as a supervised approach. Conditional random fields as the supervised method, and least confidence and information density as 2 selection criteria for active learning framework were used. The effect of incremental learning vs standard learning on the robustness of the models within the active learning framework with different selection criteria was also investigated. The following 2 clinical data sets were used for evaluation: the Informatics for Integrating Biology and the Bedside/Veteran Affairs (i2b2/VA) 2010 natural language processing challenge and the Shared Annotated Resources/Conference and Labs of the Evaluation Forum (ShARe/CLEF) 2013 eHealth Evaluation Lab. Results The annotation effort saved by active learning to achieve the same effectiveness as supervised learning is up to 77%, 57%, and 46% of the total number of sequences, tokens, and concepts, respectively. Compared with the random sampling baseline, the saving is at least doubled. Conclusion Incremental active learning is a promising approach for building effective and robust medical concept extraction models while significantly reducing the burden of manual annotation.

scholarly journals Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

2020 ◽  
Author(s):  
Juntao Li ◽  
Ruidan He ◽  
Hai Ye ◽  
Hwee Tou Ng ◽  
Lidong Bing ◽  
...  
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Language Model ◽  
Language Models ◽  
Low Resource ◽  
Performance Improvements ◽  
Domain Specific ◽  
High Resource ◽  
Significant Performance ◽  
Cross Lingual

Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks. Through training on one hundred languages and terabytes of texts, cross-lingual language models have proven to be effective in leveraging high-resource languages to enhance low-resource language processing and outperform monolingual models. In this paper, we further investigate the cross-lingual and cross-domain (CLCD) setting when a pretrained cross-lingual language model needs to adapt to new domains. Specifically, we propose a novel unsupervised feature decomposition method that can automatically extract domain-specific features and domain-invariant features from the entangled pretrained cross-lingual representations, given unlabeled raw texts in the source language. Our proposed model leverages mutual information estimation to decompose the representations computed by a cross-lingual model into domain-invariant and domain-specific parts. Experimental results show that our proposed method achieves significant performance improvements over the state-of-the-art pretrained cross-lingual language model in the CLCD setting.

scholarly journals Markup: A Web-Based Annotation Tool Powered by Active Learning

2021 ◽  
Vol 3 ◽  
Author(s):  
Samuel Dobbie ◽  
Huw Strafford ◽  
W. Owen Pickrell ◽  
Beata Fonferko-Shadrach ◽  
Carys Jones ◽  
...  
Keyword(s):  
Active Learning ◽  
Language Processing ◽  
Healthcare Setting ◽  
Free Text ◽  
Annotation Tool ◽  
Web Based ◽  
Automated Mapping ◽  
Unified Medical Language System ◽  
Domain Specific ◽  
Health And Social Care

Across various domains, such as health and social care, law, news, and social media, there are increasing quantities of unstructured texts being produced. These potential data sources often contain rich information that could be used for domain-specific and research purposes. However, the unstructured nature of free-text data poses a significant challenge for its utilisation due to the necessity of substantial manual intervention from domain-experts to label embedded information. Annotation tools can assist with this process by providing functionality that enables the accurate capture and transformation of unstructured texts into structured annotations, which can be used individually, or as part of larger Natural Language Processing (NLP) pipelines. We present Markup (https://www.getmarkup.com/) an open-source, web-based annotation tool that is undergoing continued development for use across all domains. Markup incorporates NLP and Active Learning (AL) technologies to enable rapid and accurate annotation using custom user configurations, predictive annotation suggestions, and automated mapping suggestions to both domain-specific ontologies, such as the Unified Medical Language System (UMLS), and custom, user-defined ontologies. We demonstrate a real-world use case of how Markup has been used in a healthcare setting to annotate structured information from unstructured clinic letters, where captured annotations were used to build and test NLP applications.

scholarly journals Drift Compensation on Massive Online Electronic-Nose Responses

Chemosensors ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 78
Author(s):  
Jianhua Cao ◽  
Tao Liu ◽  
Jianjun Chen ◽  
Tao Yang ◽  
Xiuxiu Zhu ◽  
...  
Keyword(s):  
Active Learning ◽  
Gas Sensor ◽  
Electronic Nose ◽  
Effective Means ◽  
Learning Paradigm ◽  
Class Label ◽  
Learning Framework ◽  
Sensor Drift ◽  
Drift Compensation ◽  
Noisy Labels

Gas sensor drift is an important issue of electronic nose (E-nose) systems. This study follows this concern under the condition that requires an instant drift compensation with massive online E-nose responses. Recently, an active learning paradigm has been introduced to such condition. However, it does not consider the “noisy label” problem caused by the unreliability of its labeling process in real applications. Thus, we have proposed a class-label appraisal methodology and associated active learning framework to assess and correct the noisy labels. To evaluate the performance of the proposed methodologies, we used the datasets from two E-nose systems. The experimental results show that the proposed methodology helps the E-noses achieve higher accuracy with lower computation than the reference methods do. Finally, we can conclude that the proposed class-label appraisal mechanism is an effective means of enhancing the robustness of active learning-based E-nose drift compensation.

scholarly journals Collecting specialty-related medical terms: Development and evaluation of a resource for Spanish

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Pilar López-Úbeda ◽  
Alexandra Pomares-Quimbaya ◽  
Manuel Carlos Díaz-Galiano ◽  
Stefan Schulz
Keyword(s):  
Language Processing ◽  
Classification Problem ◽  
Snomed Ct ◽  
Language Resources ◽  
Clinical Specialty ◽  
Controlled Vocabularies ◽  
Clinical Text ◽  
Domain Specific ◽  
Medical Terms ◽  
Core Vocabulary

Abstract Background Controlled vocabularies are fundamental resources for information extraction from clinical texts using natural language processing (NLP). Standard language resources available in the healthcare domain such as the UMLS metathesaurus or SNOMED CT are widely used for this purpose, but with limitations such as lexical ambiguity of clinical terms. However, most of them are unambiguous within text limited to a given clinical specialty. This is one rationale besides others to classify clinical text by the clinical specialty to which they belong. Results This paper addresses this limitation by proposing and applying a method that automatically extracts Spanish medical terms classified and weighted per sub-domain, using Spanish MEDLINE titles and abstracts as input. The hypothesis is biomedical NLP tasks benefit from collections of domain terms that are specific to clinical subdomains. We use PubMed queries that generate sub-domain specific corpora from Spanish titles and abstracts, from which token n-grams are collected and metrics of relevance, discriminatory power, and broadness per sub-domain are computed. The generated term set, called Spanish core vocabulary about clinical specialties (SCOVACLIS), was made available to the scientific community and used in a text classification problem obtaining improvements of 6 percentage points in the F-measure compared to the baseline using Multilayer Perceptron, thus demonstrating the hypothesis that a specialized term set improves NLP tasks. Conclusion The creation and validation of SCOVACLIS support the hypothesis that specific term sets reduce the level of ambiguity when compared to a specialty-independent and broad-scope vocabulary.

scholarly journals Robo-Advising: Learning Investors’ Risk Preferences via Portfolio Choices*

2020 ◽  
Author(s):  
Humoud Alsabah ◽  
Agostino Capponi ◽  
Octavio Ruiz Lacedelli ◽  
Matt Stern
Keyword(s):  
Opportunity Cost ◽  
Value Function ◽  
Risk Preference ◽  
Portfolio Decisions ◽  
Learning Framework ◽  
Portfolio Choices ◽  
Trading Decisions ◽  
Exploration Exploitation ◽  
The Value Function ◽  
Over Time

Abstract We introduce a reinforcement learning framework for retail robo-advising. The robo-advisor does not know the investor’s risk preference but learns it over time by observing her portfolio choices in different market environments. We develop an exploration–exploitation algorithm that trades off costly solicitations of portfolio choices by the investor with autonomous trading decisions based on stale estimates of investor’s risk aversion. We show that the approximate value function constructed by the algorithm converges to the value function of an omniscient robo-advisor over a number of periods that is polynomial in the state and action space. By correcting for the investor’s mistakes, the robo-advisor may outperform a stand-alone investor, regardless of the investor’s opportunity cost for making portfolio decisions.

scholarly journals Data Downlink System in the Vast IOT Node Condition Assisted by UAV, Large Intelligent Surface, and Power and Data Beacon

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5748
Author(s):  
Zhibo Zhang ◽  
Qing Chang ◽  
Na Zhao ◽  
Chen Li ◽  
Tianrun Li
Keyword(s):  
Communication Systems ◽  
Optimization Problems ◽  
Minimum Energy ◽  
Numerical Algorithms ◽  
Flight Trajectory ◽  
Performance Improvements ◽  
Minimum Energy Consumption ◽  
Significant Performance ◽  
Downlink System ◽  
The Internet Of Things

The future development of communication systems will create a great demand for the internet of things (IOT), where the overall control of all IOT nodes will become an important problem. Considering the essential issues of miniaturization and energy conservation, in this study, a new data downlink system is designed in which all IOT nodes harvest energy first and then receive data. To avoid the unsolvable problem of pre-locating all positions of vast IOT nodes, a device called the power and data beacon (PDB) is proposed. This acts as a relay station for energy and data. In addition, we model future scenes in which a communication system is assisted by unmanned aerial vehicles (UAVs), large intelligent surfaces (LISs), and PDBs. In this paper, we propose and solve the problem of determining the optimal flight trajectory to reach the minimum energy consumption or minimum time consumption. Four future feasible scenes are analyzed and then the optimization problems are solved based on numerical algorithms. Simulation results show that there are significant performance improvements in energy/time with the deployment of LISs and reasonable UAV trajectory planning.

A Solution Framework for Response Surface-Based Multiple Quality Characteristics Optimization

2018 ◽  
Vol 25 (05) ◽  
pp. 1850025
Author(s):  
Sasadhar Bera ◽  
Indrajit Mukherjee
Keyword(s):  
Response Surface ◽  
Optimization Problems ◽  
Real Life ◽  
Quality Characteristics ◽  
Operating Conditions ◽  
Simultaneous Optimization ◽  
Trade Off ◽  
Multiple Quality Characteristics ◽  
Pin On Disc ◽  
Application Potential

A common problem generally encountered during manufacturing process improvement involves simultaneous optimization of multiple ‘quality characteristics’ or so-called ‘responses’ and determining the best process operating conditions. Such a problem is also referred to as ‘multiple response optimization (MRO) problem’. The presence of interaction between the responses calls for trade-off solution. The term ‘trade-off’ is an explicit compromised solution considering the bias and variability of the responses around the specified targets. The global exact solution in such types of nonlinear optimization problems is usually unknown, and various trade-off solution approaches (based on process response surface (RS) models or without using process RS models) had been proposed by researchers over the years. Considering the prevalent and preferred solution approaches, the scope of this paper is limited to RS-based solution approaches and similar closely related solution framework for MRO problems. This paper contributes by providing a detailed step-by-step RS-based MRO solution framework. The applicability and steps of the solution framework are also illustrated using a real life in-house pin-on-disc design of experiment study. A critical review on solution approaches with details on inherent characteristic features, assumptions, limitations, application potential in manufacturing and selection norms (indicative of the application potential) of suggested techniques/methods to be adopted for implementation of framework is also provided. To instigate research in this field, scopes for future work are also highlighted at the end.

Sign in / Sign up

Export Citation Format

Share Document