Search results for: machine learning and natural language processing

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 128

Authors: Yinheng Li

Abstract:

The remarkable advancements in large language models (LLMs) have brought about significant improvements in natural language processing tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on different types of prompts, including discrete, continuous, few-shot, and zero-shot, and their impact on LLM performance. We explore various approaches to prompt design, such as manual design, optimization algorithms, and evaluation methods, to optimize LLM performance across diverse tasks. Our review covers key research studies in prompt engineering, discussing their methodologies and contributions to the field. We also delve into the challenges faced in evaluating prompt performance, given the absence of a single ”best” prompt and the importance of considering multiple metrics. In conclusion, the paper highlights the critical role of prompt design in harnessing the full potential of LLMs and provides insights into the combination of manual design, optimization techniques, and rigorous evaluation for more effective and efficient use of LLMs in various Natural Language Processing (NLP) tasks.

Keywords: in-context learning, prompt engineering, zero-shot learning, large language models

Procedia PDF Downloads 81

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 106

Authors: Khaled M. Alhawiti

Abstract:

Reading capability is a major segment of language competency. On the other hand, discovering topical writings at a fitting level for outside and second language learners is a test for educators. We address this issue utilizing natural language preparing innovation to survey reading level and streamline content. In the connection of outside and second-language learning, existing measures of reading level are not appropriate to this errand. Related work has demonstrated the profit of utilizing measurable language preparing procedures; we expand these thoughts and incorporate other potential peculiarities to measure intelligibility. In the first piece of this examination, we join characteristics from measurable language models, customary reading level measures and other language preparing apparatuses to deliver a finer technique for recognizing reading level. We examine the execution of human annotators and assess results for our finders concerning human appraisals. A key commitment is that our identifiers are trainable; with preparing and test information from the same space, our finders beat more general reading level instruments (Flesch-Kincaid and Lexile). Trainability will permit execution to be tuned to address the needs of specific gatherings or understudies.

Keywords: natural language processing, trainability, syntactic simplification tools, education

Procedia PDF Downloads 490

Authors: Zzibu Mark Brian

Abstract:

As software systems become increasingly complex, ensuring code security is a growing concern. Traditional vulnerability detection methods often rely on manual code reviews or static analysis tools, which can be time-consuming and prone to errors. This paper presents a distinct approach to enhancing code security by leveraging artificial intelligence (AI) and machine learning (ML) techniques. Our proposed system utilizes a combination of natural language processing (NLP) and deep learning algorithms to identify and classify vulnerabilities in real-world codebases. By analyzing vast amounts of open-source code data, our AI-powered tool learns to recognize patterns and anomalies indicative of security weaknesses. We evaluated our system on a dataset of over 10,000 open-source projects, achieving an accuracy rate of 92% in detecting known vulnerabilities. Furthermore, our tool identified previously unknown vulnerabilities in popular libraries and frameworks, demonstrating its potential for improving software security.

Keywords: AI, machine language, cord security, machine leaning

Procedia PDF Downloads 36

Authors: Sanskar, Abhinav Pal, Aryush Gupta, Sushil Kumar Mishra

Abstract:

One of the critical and tedious assignments in agricultural practices is the detection of diseases on vegetation. Agricultural production is very important in today’s economy because plant diseases are common, and early detection of plant diseases is important in agriculture. Automatic detection of such early diseases is useful because it reduces control efforts in large productive farms. Using digital image processing and machine learning algorithms, this paper presents a method for plant disease detection. Detection of the disease occurs on different leaves of the plant. The proposed system for plant disease detection is simple and computationally efficient, requiring less time than learning-based approaches. The accuracy of various plant and foliar diseases is calculated and presented in this paper.

Keywords: plant diseases, machine learning, image processing, deep learning

Procedia PDF Downloads 7

Authors: Amal Alshahrani, Allan Ramsay

Abstract:

Paraphrasing is one of the important tasks in natural language processing; i.e. alternative ways to express the same concept by using different words or phrases. Paraphrases can be used in many natural language applications, such as Information Retrieval, Machine Translation, Question Answering, Text Summarization, or Information Extraction. To obtain pairs of sentences that are paraphrases we create a system that automatically extracts paraphrases from a corpus, which is built from different sources of news article since these are likely to contain paraphrases when they report the same event on the same day. There are existing simple standard approaches (e.g. TF-IDF vector space, cosine similarity) and alignment technique (e.g. Dynamic Time Warping (DTW)) for extracting paraphrase which have been applied to the English. However, the performance of these approaches could be affected when they are applied to another language, for instance Arabic language, due to the presence of phenomena which are not present in English, such as Free Word Order, Zero copula, and Pro-dropping. These phenomena will affect the performance of these algorithms. Thus, if we can analysis how the existing algorithms for English fail for Arabic then we can find a solution for Arabic. The results are promising.

Keywords: natural language processing, TF-IDF, cosine similarity, dynamic time warping (DTW)

Procedia PDF Downloads 386

Authors: Avinash Malladhi

Abstract:

Forensic accounting is a specialized field that involves the application of accounting principles, investigative skills, and legal knowledge to detect and prevent fraud. With the rise of big data and technological advancements, artificial intelligence (AI) and machine learning (ML) algorithms have emerged as powerful tools for forensic accountants to enhance their fraud detection capabilities. In this paper, we review and analyze various AI/ML algorithms that are commonly used in forensic accounting, including supervised and unsupervised learning, deep learning, natural language processing Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Support Vector Machines (SVMs), Decision Trees, and Random Forests. We discuss their underlying principles, strengths, and limitations and provide empirical evidence from existing research studies demonstrating their effectiveness in detecting financial fraud. We also highlight potential ethical considerations and challenges associated with using AI/ML in forensic accounting. Furthermore, we highlight the benefits of these technologies in improving fraud detection and prevention in forensic accounting.

Keywords: AI, machine learning, forensic accounting & fraud detection, anti money laundering, Benford's law, fraud triangle theory

Procedia PDF Downloads 93

Authors: Subodh Chandra Shakya, Rajendra Sapkota, Aakash Tamang, Shushant Pudasaini, Sujan Adhikari, Sajjan Adhikari

Abstract:

Lots of efforts have been made in order to measure the semantic similarity between the text corpora in the documents. Techniques have been evolved to measure the similarity of two documents. One such state-of-art technique in the field of Natural Language Processing (NLP) is word to vector models, which converts the words into their word-embedding and measures the similarity between the vectors. We found this to be quite useful for the task of resume ranking. So, this research paper is the implementation of the word2vec model along with other Natural Language Processing techniques in order to rank the resumes for the particular job description so as to automate the process of hiring. The research paper proposes the system and the findings that were made during the process of building the system.

Keywords: chunking, document similarity, information extraction, natural language processing, word2vec, word embedding

Procedia PDF Downloads 158

Authors: Anes Enakoa, Yawei Liang

Abstract:

Question Answering (QA) system is one of the most important and demanding tasks in the field of Natural Language Processing (NLP). In QA systems, the answer generation task generates a list of candidate answers to the user's question, in which only one answer is correct. Answer selection is one of the main components of the QA, which is concerned with selecting the best answer choice from the candidate answers suggested by the system. However, the selection process can be very challenging especially in Arabic due to its particularities. To address this challenge, an approach is proposed to answer questions with multiple answer choices for Arabic QA systems based on Textual Entailment (TE) recognition. The developed approach employs a Support Vector Machine that considers lexical, semantic and syntactic features in order to recognize the entailment between the generated hypotheses (H) and the text (T). A set of experiments has been conducted for performance evaluation and the overall performance of the proposed method reached an accuracy of 67.5% with C@1 score of 80.46%. The obtained results are promising and demonstrate that the proposed method is effective for TE recognition task.

Keywords: information retrieval, machine learning, natural language processing, question answering, textual entailment

Procedia PDF Downloads 145

Authors: Netanel Stern

Abstract:

Artificial intelligence (AI) algorithms have emerged as powerful tools in the field of psychiatry, offering new possibilities for enhancing diagnosis and treatment outcomes. This article explores the utilization of AI algorithms in psychiatry, highlighting their potential to revolutionize patient care. Various AI algorithms, including machine learning, natural language processing (NLP), reinforcement learning, clustering, and Bayesian networks, are discussed in detail. Moreover, ethical considerations and future directions for research and implementation are addressed.

Keywords: AI, software engineering, psychiatry, neuroimaging

Procedia PDF Downloads 116

Authors: Dalila Souilem, Salma Boumiza, Abdelkarim Abdelkader

Abstract:

The Clarifier Dialogue Interface (CDI) is a part of an online teaching system based on human-machine communication in learning situation. This interface used in the system during the learning action specifically in the evaluation step, to clarify ambiguities in the learner's response. The CDI can generate patterns allowing access to an information system, using the selectors associated with lexical units. To instantiate these patterns, the user request (especially learner’s response), must be analyzed and interpreted to deduce the canonical form, the semantic form and the subject of the sentence. For the efficiency of this interface at the interpretation level, a set of substitution operators is carried out in order to extend the possibilities of manipulation with a natural language. A second approach that will be presented in this paper focuses on the object languages with new prospects such as combination of natural language with techniques of handling information system in the area of online education. So all operators, the CDI and other interfaces associated to the domain expertise and teaching strategies will be unified using FRAME representation form.

Keywords: dialogue, e-learning, FRAME, information system, natural language

Procedia PDF Downloads 377

Authors: Irene Yi

Abstract:

Machine learning, natural language processing, and neural network models of language are becoming more and more prevalent in the fields of technology and linguistics today. Training data for machines are at best, large corpora of human literature and at worst, a reflection of the ugliness in society. Computational linguistics is a growing field dealing with such issues of data collection for technological development. Machines have been trained on millions of human books, only to find that in the course of human history, derogatory and sexist adjectives are used significantly more frequently when describing females in history and literature than when describing males. This is extremely problematic, both as training data, and as the outcome of natural language processing. As machines start to handle more responsibilities, it is crucial to ensure that they do not take with them historical sexist and misogynistic notions. This paper gathers data and algorithms from neural network models of language having to deal with syntax, semantics, sociolinguistics, and text classification. Computational analysis on such linguistic data is used to find patterns of misogyny. Results are significant in showing the existing intentional and unintentional misogynistic notions used to train machines, as well as in developing better technologies that take into account the semantics and syntax of text to be more mindful and reflect gender equality. Further, this paper deals with the idea of non-binary gender pronouns and how machines can process these pronouns correctly, given its semantic and syntactic context. This paper also delves into the implications of gendered grammar and its effect, cross-linguistically, on natural language processing. Languages such as French or Spanish not only have rigid gendered grammar rules, but also historically patriarchal societies. The progression of society comes hand in hand with not only its language, but how machines process those natural languages. These ideas are all extremely vital to the development of natural language models in technology, and they must be taken into account immediately.

Keywords: computational analysis, gendered grammar, misogynistic language, neural networks

Procedia PDF Downloads 119

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 57

Authors: Xu Jiaqiao

Abstract:

Text sentiment analysis is an important branch of natural language processing. This technology is widely used in public opinion analysis and web surfing recommendations. At present, the mainstream sentiment analysis methods include three parts: sentiment analysis based on a sentiment dictionary, based on traditional machine learning, and based on deep learning. This paper mainly analyzes and compares the advantages and disadvantages of the SVM method of traditional machine learning and the Long Short-term Memory (LSTM) method of deep learning in the field of Chinese sentiment analysis, using Chinese comments on Sina Microblog as the data set. Firstly, this paper classifies and adds labels to the original comment dataset obtained by the web crawler, and then uses Jieba word segmentation to classify the original dataset and remove stop words. After that, this paper extracts text feature vectors and builds document word vectors to facilitate the training of the model. Finally, SVM and LSTM models are trained respectively. After accuracy calculation, it can be obtained that the accuracy of the LSTM model is 85.80%, while the accuracy of SVM is 91.07%. But at the same time, LSTM operation only needs 2.57 seconds, SVM model needs 6.06 seconds. Therefore, this paper concludes that: compared with the SVM model, the LSTM model is worse in accuracy but faster in processing speed.

Keywords: sentiment analysis, support vector machine, long short-term memory, Chinese microblog comments

Procedia PDF Downloads 94

Authors: Christopher Schwarz, Katrin Riegler, Erwin Zinser

Abstract:

The management of outsourcing relationships between IT service providers and their customers proofs to be a critical issue that has to be stipulated by means of Service Level Agreements (SLAs). Since service requirements differ from customer to customer, SLA content and language structures vary largely, standardized SLA templates may not be used and an automated processing of SLA content is not possible. Hence, SLA management is usually a time-consuming and inefficient manual process. For overcoming these challenges, this paper presents an innovative and ITIL V3-conform approach for automated SLA design and management using controlled natural language in enterprise collaboration portals. The proposed novel concept is based on a self-developed controlled natural language that follows a subject-predicate-object approach to specify well-defined SLA content structures that act as templates for customized contracts and support automated SLA processing. The derived results eventually enable IT service providers to automate several SLA request, approval and negotiation processes by means of workflows and business rules within an enterprise collaboration portal. The illustrated prototypical realization gives evidence of the practical relevance in service-oriented scenarios as well as the high flexibility and adaptability of the presented model. Thus, the prototype enables the automated creation of well defined, customized SLA documents, providing a knowledge representation that is both human understandable and machine processable.

Keywords: automated processing, controlled natural language, knowledge representation, information technology outsourcing, service level management

Procedia PDF Downloads 432

Authors: Migena Ceyhan, Zeynep Orhan, Dimitrios Karras

Abstract:

People in modern societies are continuously sharing their experiences, emotions, and thoughts in different areas of life. The information reaches almost everyone in real-time and can have an important impact in shaping people’s way of living. This phenomenon is very well recognized and advantageously used by the market representatives, trying to earn the most from this means. Given the abundance of information, people and organizations are looking for efficient tools that filter the countless data into important information, ready to analyze. This paper is a modest contribution in this field, describing the process of automatically classifying social media comments in the Turkish language into positive or negative. Once data is gathered and preprocessed, feature sets of selected single words or groups of words are build according to the characteristics of language used in the texts. These features are used later to train, and test a system according to different machine learning algorithms (Naïve Bayes, Sequential Minimal Optimization, J48, and Bayesian Linear Regression). The resultant high accuracies can be important feedback for decision-makers to improve the business strategies accordingly.

Keywords: feature selection, machine learning, natural language processing, sentiment analysis, social media reviews

Procedia PDF Downloads 146

Authors: Saugata Bose, Ritambhra Korpal

Abstract:

The internet has increased the copy-paste scenarios amongst students as well as amongst researchers leading to different levels of plagiarized documents. For this reason, much of research is focused on for detecting plagiarism automatically. In this paper, an initiative is discussed where Natural Language Processing (NLP) techniques as well as supervised machine learning algorithms have been combined to detect plagiarized texts. Here, the major emphasis is on to construct a framework which detects external plagiarism from monolingual texts successfully. For successfully detecting the plagiarism, n-gram frequency comparison approach has been implemented to construct the model framework. The framework is based on 120 characteristics which have been extracted during pre-processing the documents using NLP approach. Afterwards, filter metrics has been applied to select most relevant characteristics and then supervised classification learning algorithm has been used to classify the documents in four levels of plagiarism. Confusion matrix was built to estimate the false positives and false negatives. Our plagiarism framework achieved a very high the accuracy score.

Keywords: lexical matching, shallow NLP, supervised machine learning algorithm, word n-gram

Procedia PDF Downloads 357

Authors: Ebipatei Victoria Tunyan, T. A. Cao, Cheol Young Ock

Abstract:

Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.

Keywords: subjective bias detection, machine learning, BERT–BiLSTM–Attention, text classification, natural language processing

Procedia PDF Downloads 130

Authors: James Jr. Mashiyane, Risuna Nkolele, Stephanie J. Müller, Gciniwe S. Dlamini, Rebone L. Meraba, Darlington S. Mapiye

Abstract:

When performing language tasks in natural language processing (NLP), the dimensionality of word embeddings is chosen either ad-hoc or is calculated by optimizing the Pairwise Inner Product (PIP) loss. The PIP loss is a metric that measures the dissimilarity between word embeddings, and it is obtained through matrix perturbation theory by utilizing the unitary invariance of word embeddings. Unlike in natural language, in genomics, especially in genome sequence processing, unlike in natural language processing, there is no notion of a “word,” but rather, there are sequence substrings of length k called k-mers. K-mers sizes matter, and they vary depending on the goal of the task at hand. The dimensionality of word embeddings in NLP has been studied using the matrix perturbation theory and the PIP loss. In this paper, the sufficiency and reliability of applying word-embedding algorithms to various genomic sequence datasets are investigated to understand the relationship between the k-mer size and their embedding dimension. This is completed by studying the scaling capability of three embedding algorithms, namely Latent Semantic analysis (LSA), Word2Vec, and Global Vectors (GloVe), with respect to the k-mer size. Utilising the PIP loss as a metric to train embeddings on different datasets, we also show that Word2Vec outperforms LSA and GloVe in accurate computing embeddings as both the k-mer size and vocabulary increase. Finally, the shortcomings of natural language processing embedding algorithms in performing genomic tasks are discussed.

Keywords: word embeddings, k-mer embedding, dimensionality reduction

Procedia PDF Downloads 137

Authors: Lai Wenfang

Abstract:

Tthis study will describe how to use artificial intelligence (AI) technology to build the user-oriented platform for integrated archival service. The platform will be launched in 2020 by the National Archives Administration (NAA) in Taiwan. With the progression of information communication technology (ICT) the NAA has built many systems to provide archival service. In order to cope with new challenges, such as new ICT, artificial intelligence or blockchain etc. the NAA will try to use the natural language processing (NLP) and machine learning (ML) skill to build a training model and propose suggestions based on the data sent to the platform. NAA expects the platform not only can automatically inform the sending agencies’ staffs which records catalogues are against the transfer or destroy rules, but also can use the model to find the details hidden in the catalogues and suggest NAA’s staff whether the records should be or not to be, to shorten the auditing time. The platform keeps all the users’ browse trails; so that the platform can predict what kinds of archives user could be interested and recommend the search terms by visualization, moreover, inform them the new coming archives. In addition, according to the Archives Act, the NAA’s staff must spend a lot of time to mark or remove the personal data, classified data, etc. before archives provided. To upgrade the archives access service process, the platform will use some text recognition pattern to black out automatically, the staff only need to adjust the error and upload the correct one, when the platform has learned the accuracy will be getting higher. In short, the purpose of the platform is to deduct the government digital transformation and implement the vision of a service-oriented smart government.

Keywords: artificial intelligence, natural language processing, machine learning, visualization

Procedia PDF Downloads 174

Authors: Usama Shahid, Muhammad Zunnurain Hussain

Abstract:

This research paper presents a comprehensive analysis of a sentiment analysis approach that employs valence and arousal as its foundational pillars, in comparison to traditional techniques. Sentiment analysis is an indispensable task in natural language processing that involves the extraction of opinions and emotions from textual data. The valence and arousal dimensions, representing the intensity and positivity/negativity of emotions, respectively, enable the creation of four quadrants, each representing a specific emotional state. The study seeks to determine the impact of utilizing these quadrants to identify distinct emotional states on the accuracy and efficiency of sentiment analysis, in comparison to traditional techniques. The results reveal that the valence and arousal-based approach outperforms other approaches, particularly in identifying nuanced emotions that may be missed by conventional methods. The study's findings are crucial for applications such as social media monitoring and market research, where the accurate classification of emotions and opinions is paramount. Overall, this research highlights the potential of using valence and arousal as a framework for sentiment analysis and offers invaluable insights into the benefits of incorporating specific types of emotions into the analysis. These findings have significant implications for researchers and practitioners in the field of natural language processing, as they provide a basis for the development of more accurate and effective sentiment analysis tools.

Keywords: sentiment analysis, valence and arousal, emotional states, natural language processing, machine learning, text analysis, sentiment classification, opinion mining

Procedia PDF Downloads 100

Authors: Rohan Bhasin

Abstract:

Agrammatism in non-fluent Aphasia Cases can be defined as a language disorder wherein a patient can only use content words ( nouns, verbs and adjectives ) for communication and their speech is devoid of functional word types like conjunctions and articles, generating speech of with extremely rudimentary grammar . Past approaches involve Speech Therapy of some order with conversation analysis used to analyse pre-therapy speech patterns and qualitative changes in conversational behaviour after therapy. We describe this approach as a novel method to generate functional words (prepositions, articles, ) around content words ( nouns, verbs and adjectives ) using a combination of Natural Language Processing and Deep Learning algorithms. The applications of this approach can be used to assist communication. The approach the paper investigates is : LSTMs or Seq2Seq: A sequence2sequence approach (seq2seq) or LSTM would take in a sequence of inputs and output sequence. This approach needs a significant amount of training data, with each training data containing pairs such as (content words, complete sentence). We generate such data by starting with complete sentences from a text source, removing functional words to get just the content words. However, this approach would require a lot of training data to get a coherent input. The assumptions of this approach is that the content words received in the inputs of both text models are to be preserved, i.e, won't alter after the functional grammar is slotted in. This is a potential limit to cases of severe Agrammatism where such order might not be inherently correct. The applications of this approach can be used to assist communication mild Agrammatism in non-fluent Aphasia Cases. Thus by generating these function words around the content words, we can provide meaningful sentence options to the patient for articulate conversations. Thus our project translates the use case of generating sentences from content-specific words into an assistive technology for non-Fluent Aphasia Patients.

Keywords: aphasia, expressive aphasia, assistive algorithms, neurology, machine learning, natural language processing, language disorder, behaviour disorder, sequence to sequence, LSTM

Procedia PDF Downloads 164

Authors: Suraj Gururaj, Sumantha Udupa U.

Abstract:

Browsing the Web has emerged as the de facto activity performed on the Internet. Although browsing gets tracked, the manageability aspect of Web browsing history is very poor. In this paper, we have a workable solution implemented by using machine learning and natural language processing techniques for efficient manageability of user’s browsing history. The significance of adding such a capability to a Web browser is that it ensures efficient and quick information retrieval from browsing history, which currently is very challenging. Our solution guarantees that any important websites visited in the past can be easily accessible because of the intelligent and automatic classification. In a nutshell, our solution-based paper provides an implementation as a browser extension by intelligently classifying the browsing history into most relevant category automatically without any user’s intervention. This guarantees no information is lost and increases productivity by saving time spent revisiting websites that were of much importance.

Keywords: adhoc retrieval, Chrome extension, supervised learning, tile, Web personalization

Procedia PDF Downloads 376

Authors: Ali Raza, Shafiq Ur Rehman Khan, Raja Sher Afgun Usmani, Asif Raza, Basit Umair

Abstract:

Detection of Fake news and missing information is gaining popularity, especially after the advancement in social media and online news platforms. Social media platforms are the main and speediest source of fake news propagation, whereas online news websites contribute to fake news dissipation. In this study, we propose a framework to detect fake news using the temporal features of text and consider user feedback to identify whether the news is fake or not. In recent studies, the temporal features in text documents gain valuable consideration from Natural Language Processing and user feedback and only try to classify the textual data as fake or true. This research article indicates the impact of recurring and non-recurring events on fake and true news. We use two models BERT and Bi-LSTM to investigate, and it is concluded from BERT we get better results and 70% of true news are recurring and rest of 30% are non-recurring.

Keywords: natural language processing, fake news detection, machine learning, Bi-LSTM

Procedia PDF Downloads 22

Authors: Jean Marie Tshimula, Atsushi Togashi

Abstract:

We develop a data-science approach for providing an interactive visualization and predictive models to find insights into the projects' historical data in order for stakeholders understand some unseen opportunities in the African market that might escape them behind the online project portfolio of the African Development Bank. This machine learning-based web application identifies the market trend of the fastest growing economies across the continent as well skyrocketing sectors which have a significant impact on the future of business in Africa. Owing to this, the approach is tailored to predict where the investment needs are the most required. Moreover, we create a corpus that includes the descriptions of over more than 1,200 projects that approximately cover 14 sectors designed for some of 53 African countries. Then, we sift out this large amount of semi-structured data for extracting tiny details susceptible to contain some directions to follow. In the light of the foregoing, we have applied the combination of Latent Dirichlet Allocation and Random Forests at the level of the analysis module of our methodology to highlight the most relevant topics that investors may focus on for investing in Africa.

Keywords: machine learning, topic modeling, natural language processing, big data

Procedia PDF Downloads 168

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long short-term memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: dialogue management, response generation, deep learning, evaluation

Procedia PDF Downloads 167

Authors: Kaoutar Ben Azzou, Hanaa Talei

Abstract:

Human resources is an important department in each organization as it manages the life cycle of employees from recruitment training to retirement or termination of contracts. The recruitment process starts with a job opening, followed by a selection of the best-fit candidates from all applicants. Matching the best profile for a job position requires a manual way of looking at many CVs, which requires hours of work that can sometimes lead to choosing not the best profile. The work presented in this paper aims at reducing the workload of HR personnel by automating the preliminary stages of the candidate screening process, thereby fostering a more streamlined recruitment workflow. This tool introduces an automated system designed to help with the recruitment process by scanning candidates' CVs, extracting pertinent features, and employing machine learning algorithms to decide the most fitting job profile for each candidate. Our work employs natural language processing (NLP) techniques to identify and extract key features from unstructured text extracted from a CV, such as education, work experience, and skills. Subsequently, the system utilizes these features to match candidates with job profiles, leveraging the power of classification algorithms.

Keywords: automated recruitment, candidate screening, machine learning, human resources management

Procedia PDF Downloads 56

Authors: Muhammad Bilal Shaikh

Abstract:

Mineral processing plants play a pivotal role in extracting valuable minerals from raw ores, contributing significantly to various industries. However, the optimization of plant throughput remains a complex challenge, necessitating innovative approaches for increased efficiency and productivity. This research paper investigates the application of Multimodal Artificial Intelligence (MAI) techniques to address this challenge, aiming to improve overall plant throughput in mineral processing operations. The integration of multimodal AI leverages a combination of diverse data sources, including sensor data, images, and textual information, to provide a holistic understanding of the complex processes involved in mineral extraction. The paper explores the synergies between various AI modalities, such as machine learning, computer vision, and natural language processing, to create a comprehensive and adaptive system for optimizing mineral processing plants. The primary focus of the research is on developing advanced predictive models that can accurately forecast various parameters affecting plant throughput. Utilizing historical process data, machine learning algorithms are trained to identify patterns, correlations, and dependencies within the intricate network of mineral processing operations. This enables real-time decision-making and process optimization, ultimately leading to enhanced plant throughput. Incorporating computer vision into the multimodal AI framework allows for the analysis of visual data from sensors and cameras positioned throughout the plant. This visual input aids in monitoring equipment conditions, identifying anomalies, and optimizing the flow of raw materials. The combination of machine learning and computer vision enables the creation of predictive maintenance strategies, reducing downtime and improving the overall reliability of mineral processing plants. Furthermore, the integration of natural language processing facilitates the extraction of valuable insights from unstructured textual data, such as maintenance logs, research papers, and operator reports. By understanding and analyzing this textual information, the multimodal AI system can identify trends, potential bottlenecks, and areas for improvement in plant operations. This comprehensive approach enables a more nuanced understanding of the factors influencing throughput and allows for targeted interventions. The research also explores the challenges associated with implementing multimodal AI in mineral processing plants, including data integration, model interpretability, and scalability. Addressing these challenges is crucial for the successful deployment of AI solutions in real-world industrial settings. To validate the effectiveness of the proposed multimodal AI framework, the research conducts case studies in collaboration with mineral processing plants. The results demonstrate tangible improvements in plant throughput, efficiency, and cost-effectiveness. The paper concludes with insights into the broader implications of implementing multimodal AI in mineral processing and its potential to revolutionize the industry by providing a robust, adaptive, and data-driven approach to optimizing plant operations. In summary, this research contributes to the evolving field of mineral processing by showcasing the transformative potential of multimodal artificial intelligence in enhancing plant throughput. The proposed framework offers a holistic solution that integrates machine learning, computer vision, and natural language processing to address the intricacies of mineral extraction processes, paving the way for a more efficient and sustainable future in the mineral processing industry.

Keywords: multimodal AI, computer vision, NLP, mineral processing, mining

Procedia PDF Downloads 68

Authors: Sangeeta Palekar, Neeraj Rangwani, Akash Poddar, Jayu Kalambe

Abstract:

The bio-medical analysis is an indispensable procedure for identifying health-related diseases like diabetes. Monitoring the glucose level in our body regularly helps us identify hyperglycemia and hypoglycemia, which can cause severe medical problems like nerve damage or kidney diseases. This paper presents a method for predicting the glucose concentration in blood samples using image processing and machine learning algorithms. The glucose solution is prepared by the glucose oxidase (GOD) and peroxidase (POD) method. An experimental database is generated based on the colorimetric technique. The image of the glucose solution is captured by the raspberry pi camera and analyzed using image processing by extracting the RGB, HSV, LUX color space values. Regression algorithms like multiple linear regression, decision tree, RandomForest, and XGBoost were used to predict the unknown glucose concentration. The multiple linear regression algorithm predicts the results with 97% accuracy. The image processing and machine learning-based approach reduce the hardware complexities of existing platforms.

Keywords: artificial intelligence glucose detection, glucose oxidase, peroxidase, image processing, machine learning

Procedia PDF Downloads 203