Search results for: bug labels

Authors: Shao-Di Feng, Von-Wun Soo

Abstract:

To generate symbolic music with specific emotions is a challenging task due to symbolic music datasets that have emotion labels are scarce and incomplete. This research aims to generate more refined emotions based on the training datasets that are only labeled with four quadrants in Russel’s 2D emotion model. We focus on the theory of Music Fadernet and map arousal and valence to the low-level attributes, and build a symbolic music generation model by combining transformer and GM-VAE. We adopt an in-attention mechanism for the model and improve it by allowing modulation by conditional information. And we show the music generation model could control the generation of music according to the emotions specified by users in terms of high-level linguistic expression and by manipulating their corresponding low-level musical attributes. Finally, we evaluate the model performance using a pre-trained emotion classifier against a pop piano midi dataset called EMOPIA, and by subjective listening evaluation, we demonstrate that the model could generate music with more refined emotions correctly.

Keywords: music generation, music emotion controlling, deep learning, semi-supervised learning

Procedia PDF Downloads 90

Authors: Rosa L. Figueroa, Christopher A. Flores, Qing Zeng-Treitler

Abstract:

A regular expression consists of sequence characters which allow describing a text path. Usually, in clinical research, regular expressions are manually created by programmers together with domain experts. Lately, there have been several efforts to investigate how to generate them automatically. This article presents a text classification algorithm based on regexes. The algorithm named REX was designed, and then, implemented as a simplified method to create regexes to classify Spanish text automatically. In order to classify ambiguous cases, such as, when multiple labels are assigned to a testing example, REX includes an information gain method Two sets of data were used to evaluate the algorithm’s effectiveness in clinical text classification tasks. The results indicate that the regular expression based classifier proposed in this work performs statically better regarding accuracy and F-measure than Support Vector Machine and Naïve Bayes for both datasets.

Keywords: information gain, regular expressions, smith-waterman algorithm, text classification

Procedia PDF Downloads 321

Authors: Haojie Wang, Xun Li, Rui Yin

Abstract:

In order to solve the memorization overfitting in the model-agnostic meta-learning MAML algorithm, a method of generating mutually exclusive tasks based on data augmentation is proposed. This method generates a mutex task by corresponding one feature of the data to multiple labels so that the generated mutex task is inconsistent with the data distribution in the initial dataset. Because generating mutex tasks for all data will produce a large number of invalid data and, in the worst case, lead to an exponential growth of computation, this paper also proposes a key data extraction method that only extract part of the data to generate the mutex task. The experiments show that the method of generating mutually exclusive tasks can effectively solve the memorization overfitting in the meta-learning MAML algorithm.

Keywords: mutex task generation, data augmentation, meta-learning, text classification.

Procedia PDF Downloads 144

Authors: Cristina Giosuè, Federica Biondo, Sergio Vitale

Abstract:

In the last years, the consumers' awareness for environmental concerns has been increasing, and seafood eco-labels are considered as a possible instrument to improve both seafood markets and sustainable fishing management. In this direction, the aim of this study was to carry out a meta-analysis on consumers’ willingness to pay (WTP) for eco-labeled wild seafood, by a meta-regression. Therefore, only papers published on ISI journals were searched on “Web of Knowledge” and “SciVerse Scopus” platforms, using the combinations of the following key words: seafood, ecolabel, eco-label, willingness, WTP and premium. The dataset was built considering: paper’s and survey’s codes, year of publication, first author’s nationality, species’ taxa and family, sample size, survey’s continent and country, data collection (where and how), gender and age of consumers, brand and ΔWTP. From analysis the interest on eco labeled seafood emerged clearly, in particular in developed countries. In general, consumers declared greater willingness to pay than that actually applied for eco-label products, with difference related to taxa and brand.

Keywords: eco label, meta regression, seafood, willingness to pay

Procedia PDF Downloads 123

Authors: Stefanie Rukavina, Sascha Gruss, Steffen Walter, Holger Hoffmann, Harald C. Traue

Abstract:

OPEN-EmoRecII is an open multimodal corpus with experimentally induced emotions. In the first half of the experiment, emotions were induced with standardized picture material and in the second half during a human-computer interaction (HCI), realized with a wizard-of-oz design. The induced emotions are based on the dimensional theory of emotions (valence, arousal and dominance). These emotional sequences - recorded with multimodal data (mimic reactions, speech, audio and physiological reactions) during a naturalistic-like HCI-environment one can improve classification methods on a multimodal level. This database is the result of an HCI-experiment, for which 30 subjects in total agreed to a publication of their data including the video material for research purposes. The now available open corpus contains sensory signal of: video, audio, physiology (SCL, respiration, BVP, EMG Corrugator supercilii, EMG Zygomaticus Major) and mimic annotations.

Keywords: open multimodal emotion corpus, annotated labels, intelligent interaction

Procedia PDF Downloads 417

Authors: Leyla Esfandiari

Abstract:

Rapid, sensitive detection of nucleic acid (NA) molecules of specific sequence is of interest for a range of diverse health-related applications such as screening for genetic diseases, detecting pathogenic microbes in food and water, and identifying biological warfare agents in homeland security. Sequence-specific nucleic acid detection platforms rely on base pairing interaction between two complementary single stranded NAs, which can be detected by the optical, mechanical, or electrochemical readout. However, many of the existing platforms require amplification by polymerase chain reaction (PCR), fluorescent or enzymatic labels, and expensive or bulky instrumentation. In an effort to address these shortcomings, our research is focused on utilizing the cutting edge nanotechnology and microfluidics along with resistive pulse electrical measurements to design and develop a cost-effective, handheld and highly-sensitive nanopore-based sensor for point-of-care medical diagnostics.

Keywords: diagnostics, nanopore, nucleic acids, sensor

Procedia PDF Downloads 465

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 134

Authors: Mostafa ‘Neo’ Mohsenvand, Mohammad Rasool Izadi, Pattie Maes

Abstract:

EEG-based biometrics (user identification) has been explored on small datasets of no more than 157 subjects. Here we show that the accuracy of modern supervised methods falls rapidly as the number of users increases to a few thousand. Moreover, supervised methods require a large amount of labeled data for training which limits their applications in real-world scenarios where acquiring data for training should not take more than a few minutes. We show that using contrastive learning for pre-training, it is possible to maintain high accuracy on a dataset of 2130 subjects while only using a fraction of labels. We compare 5 different self-supervised tasks for pre-training of the encoder where our proposed method achieves the accuracy of 96.4%, improving the baseline supervised models by 22.75% and the competing self-supervised model by 3.93%. We also study the effects of the length of the signal and the number of channels on the accuracy of the user-identification models. Our results reveal that signals from temporal and frontal channels contain more identifying features compared to other channels.

Keywords: brainprint, contrastive learning, electroencephalo-gram, self-supervised learning, user identification

Procedia PDF Downloads 157

Authors: Florian Kleber, Martin Kampel

Abstract:

The increasing demand of gallium, indium and rare-earth elements for the production of electronics, e.g. solid state-lighting, photovoltaics, integrated circuits, and liquid crystal displays, will exceed the world-wide supply according to current forecasts. Recycling systems to reclaim these materials are not yet in place, which challenges the sustainability of these technologies. This paper proposes a multispectral imaging system as a basis for a vision based recognition system for valuable components of electronics waste. Multispectral images intend to enhance the contrast of images of printed circuit boards (single components, as well as labels) for further analysis, such as optical character recognition and entire printed circuit board recognition. The results show that a higher contrast is achieved in the near infrared compared to ultraviolet and visible light.

Keywords: electronics waste, multispectral imaging, printed circuit boards, rare-earth elements

Procedia PDF Downloads 416

Authors: Ijeoma Chinyere Ukonu

Abstract:

This research seeks to investigate how the globalisation of fast food has affected students’ food choice. A mixed method approach was used in this research; basically involving quantitative and qualitative methods. The quantitative method uses a self-completion questionnaire to randomly sample one hundred and four students; while the qualitative method uses a semi structured interview technique to survey four students on their knowledge and choice to consume fast food. A cross tabulation of variables and the Kruskal Wallis nonparametric test were used to analyse the quantitative data; while the qualitative data was analysed through deduction of themes, and trends from the interview transcribe. The findings revealed that globalisation has amplified the evolution of fast food, popularising it among students. Its global presence has affected students’ food choice and preference. Price, convenience, taste, and peer influence are some of the major factors affecting students’ choice of fast food. Though, students are familiar with the health effect of fast food and the significance of using food information labels for healthy choice making, their preference of fast food is more than homemade food.

Keywords: fast food, food choice, globalisation, students

Procedia PDF Downloads 292

Authors: Po-Chun Wang, Yan-Ru Lai, Sophia I. C. Lin, Alvin W. Y. Su

Abstract:

The Generative Theory of Tonal Music (GTTM) provides systematic approaches to recognizing local boundaries of music. The rules have been implemented in some automated melody segmentation algorithms. Besides, there are also deep learning methods with GTTM features applied to boundary detection tasks. However, these studies might face constraints such as a lack of or inconsistent label data. The GTTM database is currently the most widely used GTTM database, which includes manually labeled GTTM rules and local boundaries. Even so, we found some problems with these labels. They are sometimes discrepancies with GTTM rules. In addition, since it is labeled at different times by multiple musicians, they are not within the same scope in some cases. Therefore, in this paper, we examine this database with musicians from the aspect of classical music and relabel the scores. The relabeled database - GTTM Database v2.0 - will be released for academic research usage. Despite the experimental and statistical results showing that the relabeled database is more consistent, the improvement in boundary detection is not substantial. It seems that we need more clues than GTTM rules for boundary detection in the future.

Keywords: dataset, GTTM, local boundary, neural network

Procedia PDF Downloads 147

Authors: Melissa L Gould

Abstract:

The uptick in social media users during the COVID-19 lockdowns has accelerated concerns about cellphone addiction, cyberbullying, and exposure to harmful content, particularly mis- and disinformation and extremist content. The validity of these concerns is synthesized for media technologists to expose the strategies behind social media and search platform technology and explain why they restrict their children from using it. Banning cell phones in schools, increasing age limits on social media accounts, and putting warning labels on social media are some of the solutions proposed to protect young people from smartphones and social media. Largely missing from these conversations are the voices of young people (rangatahi). Instead, their lived experiences are being told and managed by adults. This presentation will outline my research that amplified the voices and lived experiences of young people by positioning them as experts. Using The Social Dilemma as a discussion prompt, the focus groups of rangatahi in Aotearoa, New Zealand, provide a space for young people to articulate their own lived experiences and respond to the dominant narratives on their generation's use of smartphones and social media.

Keywords: social media, smart phones, young people, social dilemma

Procedia PDF Downloads 34

Authors: Bhuyain Mobarok Hossain

Abstract:

Image classification and localization research is currently an important strategy in the field of computer vision. The evolution and advancement of deep learning and convolutional neural networks (CNN) have greatly improved the capabilities of object detection and image-based classification. Target detection is important to research in the field of computer vision, especially in video surveillance systems. To solve this problem, we will be applying a convolutional neural network of multiple scales at multiple locations in the image in one sliding window. Most translation networks move away from the bounding box around the area of interest. In contrast to this architecture, we consider the problem to be a classification problem where each pixel of the image is a separate section. Image classification is the method of predicting an individual category or specifying by a shoal of data points. Image classification is a part of the classification problem, including any labels throughout the image. The image can be classified as a day or night shot. Or, likewise, images of cars and motorbikes will be automatically placed in their collection. The deep learning of image classification generally includes convolutional layers; the invention of it is referred to as a convolutional neural network (CNN).

Keywords: image classification, object detection, localization, particle filter

Procedia PDF Downloads 306

Authors: Li Qingjian, Li Ke, He Chun, Huang Yong

Abstract:

In this paper, the method of combining the Pohl Seidman's deep belief network with the self-organizing neural network is proposed to classify the target. This method is mainly aimed at the high nonlinearity of the hyperspectral image, the high sample dimension and the difficulty in designing the classifier. The main feature of original data is extracted by deep belief network. In the process of extracting features, adding known labels samples to fine tune the network, enriching the main characteristics. Then, the extracted feature vectors are classified into the self-organizing neural network. This method can effectively reduce the dimensions of data in the spectrum dimension in the preservation of large amounts of raw data information, to solve the traditional clustering and the long training time when labeled samples less deep learning algorithm for training problems, improve the classification accuracy and robustness. Through the data simulation, the results show that the proposed network structure can get a higher classification precision in the case of a small number of known label samples.

Keywords: DBN, SOM, pattern classification, hyperspectral, data compression

Procedia PDF Downloads 341

Authors: Helmi Baazaoui, Mounir Zrigui

Abstract:

This study addresses the challenge of hate speech detection in Tunisian Arabic text, a critical issue for online safety and moderation. Leveraging the strengths of the AraBERT model, we fine-tuned and evaluated its performance against the Bi-LSTM model across four distinct datasets: T-HSAB, TNHS, TUNIZI-Dataset, and a newly compiled dataset with diverse labels such as Offensive Language, Racism, and Religious Intolerance. Our experimental results demonstrate that AraBERT significantly outperforms Bi-LSTM in terms of Recall, Precision, F1-Score, and Accuracy across all datasets. The findings underline the robustness of AraBERT in capturing the nuanced features of Tunisian Arabic and its superior capability in classification tasks. This research not only advances the technology for hate speech detection but also provides practical implications for social media moderation and policy-making in Tunisia. Future work will focus on expanding the datasets and exploring more sophisticated architectures to further enhance detection accuracy, thus promoting safer online interactions.

Keywords: hate speech detection, Tunisian Arabic, AraBERT, Bi-LSTM, Gemini annotation tool, social media moderation

Procedia PDF Downloads 16

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 185

Authors: Keyur Joshi, Philip Dietrich, Tjark Windisch, Markus König

Abstract:

In the field of surveillance-based fire detection, the volume of incoming data is increasing rapidly. However, the labeling of a large industrial dataset is costly due to the high annotation costs associated with current state-of-the-art methods, which often require bounding boxes or segmentation masks for model training. This paper introduces VideoAssist, a video annotation solution that utilizes a video-based foundation model to annotate entire videos with minimal effort, requiring the labeling of bounding boxes for only a few keyframes. To the best of our knowledge, VideoAssist is the first method to significantly reduce the effort required for labeling fire detection videos. The approach offers bounding box and segmentation annotations for the video dataset with minimal manual effort. Results demonstrate that the performance of labels annotated by VideoAssist is comparable to those annotated by humans, indicating the potential applicability of this approach in fire detection scenarios.

Keywords: fire detection, label annotation, foundation models, object detection, segmentation

Procedia PDF Downloads 17

Authors: P. Senthil Kumari

Abstract:

Main concerns in data mining investigation are social controls of data mining for handling ambiguity, noise, or incompleteness on text data. We describe an innovative approach for unplanned text data detection of community networks achieved by classification mechanism. In a tangible domain claim with humble secrecy backgrounds provided by community network for evading annoying content is presented on consumer message partition. To avoid this, mining methodology provides the capability to unswervingly switch the messages and similarly recover the superiority of ordering. Here we designated learning-centered mining approaches with pre-processing technique to complete this effort. Our involvement of work compact with rule-based personalization for automatic text categorization which was appropriate in many dissimilar frameworks and offers tolerance value for permits the background of comments conferring to a variety of conditions associated with the policy or rule arrangements processed by learning algorithm. Remarkably, we find that the choice of classifier has predicted the class labels for control of the inadequate documents on community network with great value of effect.

Keywords: text mining, data classification, community network, learning algorithm

Procedia PDF Downloads 509

Authors: Girma Yohannis Bade, Olga Kolesnikova, Grigori Sidorov

Abstract:

Named entity recognition (NER) is a building block for information extraction. Though the information extraction process has been automated using a variety of techniques to find and extract a piece of relevant information from unstructured documents, the discovery of targeted knowledge still poses a number of research difficulties because of the variability and lack of structure in Web data. NER, a subtask of information extraction (IE), came to exist to smooth such difficulty. It deals with finding the proper names (named entities), such as the name of the person, country, location, organization, dates, and event in a document, and categorizing them as predetermined labels, which is an initial step in IE tasks. This survey paper presents the roles and importance of NER to IE from the perspective of different algorithms and application area domains. Thus, this paper well summarizes how researchers implemented NER in particular application areas like finance, medicine, defense, business, food science, archeology, and so on. It also outlines the three types of sequence labeling algorithms for NER such as feature-based, neural network-based, and rule-based. Finally, the state-of-the-art and evaluation metrics of NER were presented.

Keywords: the role of NER, named entity recognition, information extraction, sequence labeling algorithms, named entity application area

Procedia PDF Downloads 81

Authors: B. Kahouadji, L. Guerbous, L. Lamiri, A. Mendoud

Abstract:

Recently, nanomaterials are developed in the form of nano-films, nano-crystals and nano-pores. Lanthanide phosphates as a material find extensive application as laser, ceramic, sensor, phosphor, and also in optoelectronics, medical and biological labels, solar cells and light sources. Among the different kinds of rare-earth orthophosphates, yttrium orthophosphate has been shown to be an efficient host lattice for rare earth activator ions, which have become a research focus because of their important role in the field of light display systems, lasers, and optoelectronic devices. It is in this context that the 4fn- « 4fn-1 5d transitions of rare earth in insulating materials, lying in the UV and VUV, are the aim of large number of studies .Though there has been a few reports on Eu3+, Nd3+, Pr3+,Er3+, Ce3+, Tm3+ doped YPO4. The 4fn- « 4fn-1 5d transitions of the rare earth dependent to the host-matrix, several matrices ions were used to study these transitions, in this work we are suggesting to study on a very specific class of inorganic material that are orthophosphate doped with rare earth ions. This study focused on the effect of Ce3+ concentration on the structural and optical properties of Ce3+ doped YPO4 yttrium orthophosphate with powder form prepared by the Sol Gel method.

Keywords: YPO4, Ce3+, 4fn- <->4fn-1 5d transitions, scintillator

Procedia PDF Downloads 346

Authors: Barby Jennette A. Florano

Abstract:

Dietary intake has been associated with the health and wellbeing of adults, and lifestyle related diseases. The aim of this study was to investigate whether nutrition knowledge, food label use, and food preference are associated with the dietary intake in a sample of San Jose Del Monte City, Bulacan (SJDM) adults. A sample of 148 adults, with a mean age of 20 years, completed a validated questionnaire related to their demographic, dietary intake, nutrition knowledge, food label use and food preference. Data were analyzed using Pearson correlation and there was no association between dietary intake and nutrition knowledge. However, there were positive relationships between dietary intake and food label use (r=0.1276, p<0.10), and dietary intake and food preference (r=0.1070, p<0.10). SJDM adults who use food label and have extensive food preference had better diet quality. This finding magnifies the role of nutrition education as a potential tool in health campaigns to promote healthy eating patterns and reading food labels among students and adults. Results of this study can give information for the design of future nutrition education intervention studies to assess the efficacy of nutrition knowledge and food label use among a similar sample population.

Keywords: dietary intake, nutrition knowledge, food preference, food label use

Procedia PDF Downloads 93

Authors: Gisele Ghanem Cardoso, Sandra Rech

Abstract:

Despite recent advancements, the plus-size market still faces significant gaps, as individuals with larger bodies struggle to find clothing that fits well and meets their needs. Addressing this issue, this research aims to investigate the availability of fashion products for plus-size women in both physical and online stores in Florianópolis, as well as the quantity of products available in each size. The study employs content analysis based on Bardin's framework, examining data on store locations, size ranges, and target audiences of various brands alongside observations of visual elements such as hanger sizes and the branding of specialized labels. The findings reveal a concentration of plus-size stores in peripheral areas and a limited selection of diverse, high-quality products, contrasting sharply with the access standard-sized bodies have to more prestigious fashion hubs. These results highlight how the current market structure perpetuates social exclusion, underscoring the urgent need for inclusive policies and an expanded plus-size market to promote greater equity and representation in fashion consumption.

Keywords: plus size fashion, representation, consumption, Florianópolis, product availability, social exclusion

Procedia PDF Downloads 11

Authors: Kennedy Efosa Ehimwenma, Sujatha Krishnamoorthy, Safiya Al‑Sharji

Abstract:

The probability computation of events is in the interval of [0, 1], which are values that are determined by the number of outcomes of events in a sample space S. The probability Pr(A) that an event A will never occur is 0. The probability Pr(B) that event B will certainly occur is 1. This makes both events A and B a certainty. Furthermore, the sum of probabilities Pr(E₁) + Pr(E₂) + … + Pr(Eₙ) of a finite set of events in a given sample space S equals 1. Conversely, the difference of the sum of two probabilities that will certainly occur is 0. This paper first discusses Bayes, the complement of probability, and the difference of probability for occurrences of learning-events before applying them in the prediction of learning objects in student learning. Given the sum of 1; to make a recommendation for student learning, this paper proposes that the difference of argMaxPr(S) and the probability of student-performance quantifies the weight of learning objects for students. Using a dataset of skill-set, the computational procedure demonstrates i) the probability of skill-set events that have occurred that would lead to higher-level learning; ii) the probability of the events that have not occurred that requires subject-matter relearning; iii) accuracy of the decision tree in the prediction of student performance into class labels and iv) information entropy about skill-set data and its implication on student cognitive performance and recommendation of learning.

Keywords: complement of probability, Bayes’ rule, prediction, pre-assessments, computational education, information theory

Procedia PDF Downloads 163

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 170

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: metaphor detection, deep learning, representation learning, embeddings

Procedia PDF Downloads 154

Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao

Abstract:

Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.

Keywords: OSML, BERT, text classification, one shot

Procedia PDF Downloads 101

Authors: Adam Reilly

Abstract:

The major claim of this paper is that both the English and Canadian branches of the common law have been ill-served by the 'institutional'/'remedial' taxonomy of constructive trusts; what shall be termed the 'orthodox taxonomy'.  The orthodox taxonomy is found both within the case law and the attendant academic commentary.  In truth, the orthodox taxonomy is especially dangerous because it contains a kernel of truth together with a misconception; the interplay of both has caused more harm than the misconception alone would have managed.  The kernel of truth is that some trusts arise automatically when the necessary facts occur ('institutional') and other trusts arise only by way of court order ('remedial').  The misconception is that these two labels represent an exhaustive nomenclature of two distinct 'kinds' of constructive trust such that any particular constructive trust must necessarily be 'institutional' if it is not 'remedial' and vice versa.  The central difficulty is that our understanding of 'remedial' trusts is relatively poor, with the result that anyone using the orthodox taxonomy shall be led astray in one of three ways: (i) by rejecting it wholesale; (ii) by adopting one ‘type’ of trust to the exclusion of the other (as in English law); or (iii) by applying it as an analytical device with sub-optimal results which are difficult to defend.  This paper shall seek to resolve these difficulties by clarifying the criteria for identifying and distinguishing true 'remedial' constructive trusts.  It shall then provide some working examples of how English and Canadian private law at present misunderstand constructive trusts and how that misunderstanding might be resolved once we distinguish the orthodox taxonomy's kernel of truth from the misconception outlined above.

Keywords: comparative law, constructive trusts, equitable remedies, remedial constructive trusts

Procedia PDF Downloads 143

Authors: Adrian-Gabriel Chifu, Sebastien Fournier

Abstract:

One of the challenges of natural language understanding is to deal with the subjectivity of sentences, which may express opinions and emotions that add layers of complexity and nuance. Sentiment analysis is a field that aims to extract and analyze these subjective elements from text, and it can be applied at different levels of granularity, such as document, paragraph, sentence, or aspect. Aspect-based sentiment analysis is a well-studied topic with many available data sets and models. However, there is no clear definition of what makes a sentence difficult for aspect-based sentiment analysis. In this paper, we explore this question by conducting an experiment with three data sets: ”Laptops”, ”Restaurants”, and ”MTSC” (Multi-Target-dependent Sentiment Classification), and a merged version of these three datasets. We study the impact of domain diversity and syntactic diversity on difficulty. We use a combination of classifiers to identify the most difficult sentences and analyze their characteristics. We employ two ways of defining sentence difficulty. The first one is binary and labels a sentence as difficult if the classifiers fail to correctly predict the sentiment polarity. The second one is a six-level scale based on how many of the top five best-performing classifiers can correctly predict the sentiment polarity. We also define 9 linguistic features that, combined, aim at estimating the difficulty at sentence level.

Keywords: sentiment analysis, difficulty, classification, machine learning

Procedia PDF Downloads 92

Authors: Mohammed Idaan Hassan Al-Majidi

Abstract:

An analysis of twenty one assorted brands of vegetable oils in Babylon Iraq, reveals varying levels of cholesterol content. Cholesterol was found to be present in most of the oil brands sampled using three standard methods. Cholesterol was detected in seventeen of the vegetable oil brands with concentration of less than 1 mg/ml while seven of the oil brands had cholesterol concentrations ranging between 1-4 mg/ml. Low iodine values were obtained in four of the vegetable oil brands and three of them had high acid values. High performance liquid chromatography (HPLC) confirmed the presence of cholesterol at varying concentrations in all the oil brands and gave the lowest detectable cholesterol values in all the oil brands. The Laser brand made from rapeseed had the highest cholesterol concentration of 3.2 mg/ml while Grand brand made from groundnuts had the least concentration (0.12 mg/ml) of cholesterol using HPLC analysis. Leibermann-Burchard method showed that Gino brand from palm kernel had the least concentration of cholesterol (3.86 mg/ml ±0.032) and the highest concentration of 3.996 mg/ml ±0.0404 was obtained in Sesame seed oil brand. This report is important in view of health implications of cholesterol in our diets. Consequently, we have been able to show that there is no cholesterol free oil in the market as shown on the vegetable oil brand labels. Therefore, companies producing and marketing vegetable oils are enjoined to desist from misleading the public by labeling their products as “cholesterol free”. They should indicate the amount of cholesterol present in the vegetable oil, no matter how small the quantity may be.

Keywords: vegetable oils, heart diseases, leibermann-burchard, cholesterol

Procedia PDF Downloads 260

Authors: Xinyi Le

Abstract:

In this paper, 3D printing orientations were determined through our perceptual model. Some FDM (Fused Deposition Modeling) 3D printers, which are widely used in universities and industries, often require support structures during the additive manufacturing. After removing the residual material, some surface artifacts remain at the contact points. These artifacts will damage the function and visual effect of the model. To prevent the impact of these artifacts, we present a fuzzy extreme learning machine approach to find printing directions that avoid placing supports in perceptually significant regions. The proposed approach is able to solve the evaluation problem by combing both the subjective knowledge and objective information. Our method combines the advantages of fuzzy theory, auto-encoders, and extreme learning machine. Fuzzy set theory is applied for dealing with subjective preference information, and auto-encoder step is used to extract good features without supervised labels before extreme learning machine. An extreme learning machine method is then developed successfully for training and learning perceptual models. The performance of this perceptual model will be demonstrated on both natural and man-made objects. It is a good human-computer interaction practice which draws from supporting knowledge on both the machine side and the human side.

Keywords: 3d printing, perceptual model, fuzzy evaluation, data-driven approach

Procedia PDF Downloads 439