Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
24,727
result(s) for
"BERT"
Sort by:
Here comes the night : the dark soul of Bert Berns and the dirty business of rhythm & blues
Songwriter and record producer Bert Berns' meteoric career was fueled by his pending doom. His heart damaged by rheumatic fever as a youth, Berns was not expected to live to see 21. Although his name is little remembered today, Berns went from nobody to the top of the pops, producer of monumental r&b classics, songwriter of \"Twist and Shout,\" \"My Girl Sloopy,\" \"Piece of My Heart,\" and others. His fury to succeed led Berns to use his Mafia associations to muscle Atlantic Records out of their partnership and intimidate new talents whom he had signed to his record label. Berns died at age 38 just when he was seeing his grandest plans frustrated and foiled.
Book
DPAL-BERT: A Faster and Lighter Question Answering Model
Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems. However, with the constant evolution of algorithms, data, and computing power, the increasing size and complexity of these models have led to increased training costs and reduced efficiency. This study aims to minimize the inference time of such models while maintaining computational performance. It also proposes a novel Distillation model for PAL-BERT (DPAL-BERT), specifically, employs knowledge distillation, using the PAL-BERT model as the teacher model to train two student models: DPAL-BERT-Bi and DPAL-BERT-C. This research enhances the dataset through techniques such as masking, replacement, and n-gram sampling to optimize knowledge transfer. The experimental results showed that the distilled models greatly outperform models trained from scratch. In addition, although the distilled models exhibit a slight decrease in performance compared to PAL-BERT, they significantly reduce inference time to just 0.25% of the original. This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.
Journal Article
Database of dreams : the lost quest to catalog humanity
\"Just a few years before the dawn of the digital age, Harvard psychologist Bert Kaplan set out to build the largest database of sociological information ever assembled. It was the mid-1950s, and social scientists were entranced by the human insights promised by Rorschach tests and other innovative scientific protocols. Kaplan, along with anthropologist A. I. Hallowell and a team of researchers, sought out a varied range of non-European subjects-among remote and largely non-literate peoples around the globe. Recording their dreams, stories, and innermost thoughts in a vast database, Kaplan envisioned future researchers accessing the data through the cutting-edge Readex machine. Almost immediately, however, technological developments and the obsolescence of the theoretical framework rendered the project irrelevant, and eventually it was forgotten. Kaplan's story is a tale of the search for what it means to be human, or what it came to mean in an age of rapid change in technological and social conditions. His project--call it a database of consciousness--was intended as a repository of humankind's most elusive ways of being human, as an anthropological archive; through it a veritable sluice of social knowledge was expected to flow from seemingly unlikely encounters. This is a book about those encounters--between scientists and subjects, between knowledge and machines--as well as the data that flowed out of them and the ways these were preserved and not preserved.\"-- Book jacket.
Book
BERT applications in natural language processing: a review
BERT (Bidirectional Encoder Representations from Transformers) has revolutionized Natural Language Processing (NLP) by significantly enhancing the capabilities of language models. This review study examines the complex nature of BERT, including its structure, utilization in different NLP tasks, and the further development of its design via modifications. The study thoroughly analyses the methodological aspects, conducting a comprehensive analysis of the planning process, the implemented procedures, and the criteria used to decide which data to include or exclude in the evaluation framework. In addition, the study thoroughly examines the influence of BERT on several NLP tasks, such as Sentence Boundary Detection, Tokenization, Grammatical Error Detection and Correction, Dependency Parsing, Named Entity Recognition, Part of Speech Tagging, Question Answering Systems, Machine Translation, Sentiment analysis, fake review detection and Cross-lingual transfer learning. The review study adds to the current literature by integrating ideas from multiple sources, explicitly emphasizing the problems and prospects in BERT-based models. The objective is to comprehensively comprehend BERT and its implementations, targeting both experienced researchers and novices in the domain of NLP. Consequently, the present study is expected to inspire more research endeavors, promote innovative adaptations of BERT, and deepen comprehension of its extensive capabilities in various NLP applications. The results presented in this research are anticipated to influence the advancement of future language models and add to the ongoing discourse on enhancing technology for understanding natural language.
Journal Article
Taos Society of Artists
\"\"A lavishly illustrated two-volume study of the Taos Society of Artists. Essays on the TSA and its founding plus scholarly biographical and art historical essays on twelve TSA artists with exemplary works of the artists studied\"-Provided by publisher\"-- Provided by publisher.
BOOK
Multi task opinion enhanced hybrid BERT model for mental health analysis
Understanding the nuanced emotions and points of view included in user-generated content remains challenging, even though text data analysis for mental health is a crucial instrument for assessing emotional well-being. Most current models neglect the significance of integrating viewpoints in comprehending mental health in favor of single-task learning. To offer a more thorough knowledge of mental health, in this study, we present an Opinion-Enhanced Hybrid BERT Model (Opinion-BERT), built to handle multi-task learning for simultaneous sentiment and status categorization. With the help of TextBlob and SciPy, we extracted opinions and dynamically constructed new opinion embeddings to complement the pre-trained BERT model. Using a hybrid architecture, these embeddings are integrated with the contextual embeddings of BERT, whereby the CNN and BiGRU layers collected local and sequential characteristics. This combination helps our model to identify and categorize user status and attitudes from the text more accurately, which leads to more accurate mental health assessments. When we compared the performance of Opinion-BERT to some baseline models, including BERT, RoBERTa, and DistilBERT, we found that it performed much better. Opinion-enhanced embeddings are crucial for improving performance, as demonstrated by our multi-task learning framework’s 96.77% sentiment classification accuracy of 94.22% status classification accuracy. This work provides a more nuanced understanding of emotions and psychological states by demonstrating the potential of combining opinion and sentiment data for mental health analysis in a multi-task learning environment.
Journal Article
Aspect-based sentiment-analysis using topic modelling and machine-learning
This study addresses the critical need for an accurate aspect-based sentiment-analysis (ABSA) model to understand sentiments effectively. The existing ABSA models often face challenges in accurately extracting aspects and determining sentiment polarity from textual data. Therefore, we propose a novel approach leveraging latent-Dirichlet-allocation (LDA) for aspect extraction and transformer-based bidirectional-encoder-representations from transformers (TF-BERT) for sentiment-polarity evaluation. The experiments were carried out on SemEval 2014 laptop and restaurant datasets. Also, a multi-domain dataset was generated by combining SemEval 2014, Amazon, and hospital reviews. The results demonstrate the superiority of the LDA-TF-BERT model, achieving 82.19% accuracy and 79.52% Macro-F1 score for the laptop task and 86.26% accuracy of 87.26% and 81.27% for Macro-F1 score for the restaurant task. This showcases the model's robustness and effectiveness in accurately analyzing textual data and extracting meaningful insights. The novelty of our work lies in combining LDA and TF-BERT, providing a comprehensive and accurate ABSA solution for various industries, thereby contributing significantly to the advancement of sentiment analysis techniques.
Journal Article
Survey of BERT (Bidirectional Encoder Representation Transformer) types
There are many algorithms used in Natural Language Processing( NLP) to achieve good results, such as Machine Learning (ML), Deep Learning(DL) and many other algorithms. In Natural Language Processing,the first challenges is to convert text to numbers for using by any algorithm that a researcher choose. So how can convert text to numbers? This is happen by using Word Embedding algorithms such as skip gram,bags of words,BERT and etc. Representing words as numerical vectors by relying on the contents has become one of the effective methods for analyzing texts in machine learning, so that each word is represented by a vector to determine its meaning or to know how close or distant this word from the rest of the other word. BERT(Bidirectional Encoder Representation Transformer) is one of the embedding methods. It is designed to pre-trained form left and right in all layer deep training. It is a deep language model that is used for various tasks in natural language processing. In this paper we will review the different versions and types of BERT.
Journal Article
Comprehensive study of pre-trained language models: detecting humor in news headlines
The ability to automatically understand and analyze human language attracted researchers and practitioners in the Natural Language Processing (NLP) field. Detecting humor is an NLP task needed in many areas, including marketing, politics, and news. However, such a task is challenging due to the context, emotion, culture, and rhythm. To address this problem, we have proposed a robust model called BFHumor, a BERT-Flair-based Humor detection model that detects humor through news headlines. It is an ensemble model of different state-of-the-art pre-trained models utilizing various NLP techniques. We used public humor datasets from the SemEval-2020 workshop to evaluate the proposed model. As a result, the model achieved outstanding performance with 0.51966 as Root Mean Squared Error (RMSE) and 0.62291 as accuracy. In addition, we extensively investigated the underlying reasons behind the high accuracy of the BFHumor model in humor detection tasks. To that end, we conducted two experiments on the BERT model: vocabulary level and linguistic capturing level. Our investigation shows that BERT can capture surface knowledge in the lower layers, syntactic in the middle, and semantic in the higher layers.
Journal Article
An Enhanced Aspect-Based Sentiment Analysis Model Based on RoBERTa For Text Sentiment Analysis
Using an aspect-based sentiment analysis task, sentiment polarity towards specific aspect phrases within the same sentence or document is to be identified. The process of mechanically determining the underlying attitude or opinion indicated in the text is known as sentiment analysis. One of the most important aspects of natural language processing is sentiment analysis. The RoBERTa transformer model was pretrained in a self-supervised manner using a substantial corpus of English data. This means it was pretrained solely with raw texts and an algorithmic process to generate inputs and labels from those texts. No human labelling was involved, allowing it to utilise a vast amount of publicly available data. The authors of this work provide a thorough investigation of aspect-based sentiment analysis with RoBERTa. The RoBERTa model and its salient characteristics are outlined in this work, followed by an analysis of the model’s optimisation by the authors for aspect-based sentiment analysis. The authors compare the RoBERTa model with other state-of-the-art models and evaluate its performance on multiple benchmark datasets. Our experimental results show that the RoBERTa model is effective for this important natural language processing task, outperforming competing models on sentiment analysis tasks. Based on the SemEval-2014 variant benchmarking datasets, the restaurant and laptop domains have the highest accuracy, scoring 92.35 % and 82.33 %, respectively.
Journal Article