In this thesis, we developed a comprehensive framework for sentiment analysis that takes its many aspects into account mainly for Turkish. We have also proposed several approaches specific to sentiment analysis in English only. We have accordingly made five major and three minor contributions. We generated a novel and effective feature set by combining unsupervised, semi-supervised, and supervised metrics. We then fed them as input into classical machine learning methods, and outperformed neural network models for datasets of different genres in both Turkish and English. We created a polarity lexicon with a semi-supervised domain-specific method, which has been the first approach applied for corpora in Turkish. We performed a fine morphological analysis for the sentiment classification task in Turkish by determining the polarities of morphemes. This can be adapted to other morphologically-rich or agglutinative languages as well. We have built a novel neural network architecture, which combines recurrent and recursive neural network models for English. We built novel word embeddings that exploit sentiment, syntactic, semantic, and lexical characteristics for both Turkish and English. We also redefined context windows as subclauses in modelling word representations in English. This can also be applied to other linguistic fields and natural language processing tasks. We have achieved state-of-the-art and significant results for all these original approaches. Our minor contributions include methods related to aspect-based sentiment in Turkish, parameter redefinition in the semi-supervised approach, and aspect term extraction techniques for English. This thesis can be considered the most detailed and comprehensive study made on sentiment analysis in Turkish as of July, 2020. Our work has also contributed to the opinion classification problem in English.

Recent advances in LLM have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLM to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models.

Virtual staining of tissue offers a powerful tool for transforming label-free microscopy images of unstained tissue into equivalents of histochemically stained samples. This study presents a diffusion model-based super-resolution virtual staining approach utilizing a Brownian bridge process to enhance both the spatial resolution and fidelity of label-free virtual tissue staining, addressing the limitations of traditional deep learning-based methods. Our approach integrates novel sampling techniques into a diffusion model-based image inference process to significantly reduce the variance in the generated virtually stained images, resulting in more stable and accurate outputs. Blindly applied to lower-resolution auto-fluorescence images of label-free human lung tissue samples, the diffusion-based super-resolution virtual staining model consistently outperformed conventional approaches in resolution, structural similarity and perceptual accuracy, successfully achieving a super-resolution factor of 4-5x, increasing the output space-bandwidth product by 16-25-fold compared to the input label-free microscopy images. Diffusion-based super-resolved virtual tissue staining not only improves resolution and image quality but also enhances the reliability of virtual staining without traditional chemical staining, offering significant potential for clinical diagnostics.

This paper proposes a novel prompt engineering technique called Judgment of Thought (JoT) that is specifically tailored for binary logical reasoning tasks. JoT employs three roles$\unicode{x2014}$lawyer, prosecutor, and judge$\unicode{x2014}$to facilitate more reliable and accurate reasoning by the model. In this framework, the judge utilizes a high$\unicode{x2010}$level model, while the lawyer and prosecutor utilize low$\unicode{x2010}$level models. This structure helps the judge better understand the responses from both the lawyer and prosecutor, enabling a more accurate judgment. Experimental results on large language model (LLM) benchmark datasets, such as BigBenchHard and Winogrande, demonstrate that JoT outperforms existing methods, including Chain of Thought (CoT) and Self$\unicode{x2010}$Consistency (SC), in binary logical reasoning tasks. Additionally, in real$\unicode{x2010}$world tasks, such as Fake News Detection and SMS Spam Detection, JoT shows comparable or improved performance compared to existing techniques. JoT significantly enhances the accuracy and reliability of models in binary reasoning tasks and show potential for practical applicability across various domains. Future research should aim to further broaden the applicability of JoT and optimize its implementation for real$\unicode{x2010}$world problem$\unicode{x2010}$solving.

In 2023, we are using the latest models of GPT-4 to advance program synthesis. The large language models have significantly improved the state-of-the-art for this purpose. To make these advancements more accessible, we have created a repository that connects these models to Huamn Eval. This dataset was initally developed to be used with a language model called CODEGEN on natural and programming language data. The utility of these trained models is showcased by demonstrating their competitive performance in zero-shot Python code generation on HumanEval tasks compared to previous state-of-the-art solutions. Additionally, this gives way to developing more multi-step paradigm synthesis. This benchmark features 160 diverse problem sets factorized into multistep prompts that our analysis shows significantly improves program synthesis over single-turn inputs. All code is open source at https://github.com/daniel442li/gpt-human-eval .

In this paper, we present a novel approach to simulating H.P. Lovecraft's horror literature using the ChatGPT large language model, specifically the GPT-4 architecture. Our study aims to generate text that emulates Lovecraft's unique writing style and themes, while also examining the effectiveness of prompt engineering techniques in guiding the model's output. To achieve this, we curated a prompt containing several specialized literature references and employed advanced prompt engineering methods. We conducted an empirical evaluation of the generated text by administering a survey to a sample of undergraduate students. Utilizing statistical hypothesis testing, we assessed the students' ability to distinguish between genuine Lovecraft works and those generated by our model. Our findings demonstrate that the participants were unable to reliably differentiate between the two, indicating the effectiveness of the GPT-4 model and our prompt engineering techniques in emulating Lovecraft's literary style. In addition to presenting the GPT model's capabilities, this paper provides a comprehensive description of its underlying architecture and offers a comparative analysis with related work that simulates other notable authors and philosophers, such as Dennett. By exploring the potential of large language models in the context of literary emulation, our study contributes to the body of research on the applications and limitations of these models in various creative domains.

Welcome to Feature Engineering for Machine Learning, the most comprehensive course on feature engineering available online. In this course, you will learn how to engineer features and build more powerful machine learning models. Who is this course for? So, you've made your first steps into data science, you know the most commonly used prediction models, you probably built a linear regression or a classification tree model. At this stage you're probably starting to encounter some challenges - you realize that your data set is dirty, there are lots of values missing, some variables contain labels instead of numbers, others do not meet the assumptions of the models, and on top of everything you wonder whether this is the right way to code things up.

Learn how to deal with infrequent, rare, and unseen categories. Learn how to work with skewed variables. Learn techniques used in organizations worldwide and in data competitions. Increase your repertoire of techniques to preprocess data and build more powerful machine learning models. Learn how to deal with infrequent, rare, and unseen categories.

Welcome to Feature Engineering for Machine Learning, the most comprehensive course on feature engineering available online. In this course, you will learn how to engineer features and build more powerful machine learning models. Who is this course for? So, you've made your first steps into data science, you know the most commonly used prediction models, you perhaps even built a linear regression or a classification tree model. At this stage you're probably starting to encounter some challenges - you realize that your data set is dirty, there are lots of values missing, some variables contain labels instead of numbers, others do not meet the assumptions of the models, and on top of everything you wonder whether this is the right way to code things up.

At Apple, we work every day to create products that enrich people's lives. Our Advertising Platforms group makes it possible for people around the world to easily access informative and imaginative content on their devices while helping publishers and developers promote and monetize their work. Our platforms are highly-performant, deployed at scale, and setting new standards for enabling effective advertising while protecting user privacy. We are looking for an ambitious and versatile engineer who can thrive in an Agile environment, delivering solutions to enable advanced techniques and algorithms to improve an ad network. You will work closely with Data Scientists and ML Engineers to develop and implement platform components that will allow advertising algorithms to optimize and scale.