I decided to sign up to Medium "by the other side" with the aim to publish my AI for Finance projects and empower my knowledge in these sectors, thanks to this great community! I love to analyse stocks and alternative assets prices and making inference using regressions, ensemble methods and sentiment analysis. I may still be not so capable of using Medium but I'll give it a shot! I'm so excited to start this!

Data-to-text generation focuses on generating fluent natural language responses from structured semantic representations. Such representations are compositional, allowing for the combination of atomic meaning schemata in various ways to express the rich semantics in natural language. Recently, pretrained language models (LMs) have achieved impressive results on data-to-text tasks, though it remains unclear the extent to which these LMs generalize to new semantic representations. In this work, we systematically study the compositional generalization of current state-of-the-art generation models in data-to-text tasks. By simulating structural shifts in the compositional Weather dataset, we show that T5 models fail to generalize to unseen structures. Next, we show that template-based input representations greatly improve the model performance and model scale does not trivially solve the lack of generalization. To further improve the model's performance, we propose an approach based on self-training using finetuned BLEURT for pseudo-response selection. Extensive experiments on the few-shot Weather and multi-domain SGD datasets demonstrate strong gains of our method.

Sentimental Analysis helps in quickly analyzing the numerous amount of data. Since Artificial Intelligence and its advanced technologies have started influencing different sectors. A lot of research work is taking place for developing different tools that can evolve Artificial Intelligence and Machine Learning more stronger. And Sentiment Analysis is one such topic that has created a buzz in the field of scientific and market research in the field of Natural Language Processing and Machine Learning with the help of its amazing applications. Basically, Sentiment Analysis is a Machine Learning tool.

Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills. A simple yet unexplored solution is prompt-based few-shot learning (Brown et al. 2020) which does not require gradient-based fine-tuning but instead uses a few examples in the LM context as the only source of learning. In this paper, we explore prompt-based few-shot learning in dialogue tasks. We benchmark LMs of different sizes in nine response generation tasks, which include four knowledge-grounded tasks, a task-oriented generations task, three open-chat tasks, and controlled stylistic generation, and five conversational parsing tasks, which include dialogue state tracking, graph path generation, persona information extraction, document retrieval, and internet query generation. The current largest released LM (GPT-J-6B) using prompt-based few-shot learning, and thus requiring no training, achieves competitive performance to fully trained state-of-the-art models. Moreover, we propose a novel prompt-based few-shot classifier, that also does not require any fine-tuning, to select the most appropriate prompt given a dialogue history. Finally, by combining the power of prompt-based few-shot learning and a Skill Selector, we create an end-to-end chatbot named the Few-Shot Bot (FSB), which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill.

Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training. Over the last few years, there has been a move towards data curation for multilingual ToD systems that are applicable to serve people speaking different languages. However, existing multilingual ToD datasets either have a limited coverage of languages due to the high cost of data curation, or ignore the fact that dialogue entities barely exist in countries speaking these languages. To tackle these limitations, we introduce a novel data curation method that generates GlobalWoZ -- a large-scale multilingual ToD dataset globalized from an English ToD dataset for three unexplored use cases. Our method is based on translating dialogue templates and filling them with local entities in the target-language countries. We release our dataset as well as a set of strong baselines to encourage research on learning multilingual ToD systems for real use cases.

For too many organizations, the intertwined technologies of artificial intelligence (AI) and machine learning (ML) have been long on promise but short on delivery. Increasingly, however, the fault lies not in these advanced technologies themselves, but in the challenges associated with deploying them easily and effectively to support everyday business processes. True, some AI proponents did over-promise on the field's capabilities and timetable in past decades. But a number of AI disciplines – everything from natural language processing to computer vision – have become incredibly sophisticated and powerful in recent years. AI technologies, in turn, are now powering object recognition, language translation, sentiment analysis, and a host of other use cases.

Listening to what's being said about your brand can be invaluable for any business. Humans can identify positive and negative sentiments, identify slang, sarcasm, irony, and more. However, the enormous volumes of chatter on the internet make it difficult to determine the overall public sentiments. No need to get anxious, that is exactly what sentiment analysis tools are for. Sentiment analysis tools can help you compile and analyze everything that's being said about your brand.

In this course I will cover, how to develop a Sentiment Analysis model to categorize a tweet as Positive or Negative using NLP techniques and Machine Learning Models. This is a hands on project where I will teach you the step by step process in creating and evaluating a machine learning model and finally deploying the same on Cloud platforms to let your customers interact with your model via an user interface. This course will walk you through the initial data exploration and understanding, data analysis, data pre-processing, data preparation, model building, evaluation and deployment techniques. We will explore NLP concepts and then use multiple ML algorithms to create our model and finally focus into one which performs the best on the given dataset. At the end we will learn to create an User Interface to interact with our created model and finally deploy the same on Cloud.

Topic models provide a useful text-mining tool for learning, extracting and discovering latent structures in large text corpora. Although a plethora of methods have been proposed for topic modeling, a formal theoretical investigation on the statistical identifiability and accuracy of latent topic estimation is lacking in the literature. In this paper, we propose a maximum likelihood estimator (MLE) of latent topics based on a specific integrated likelihood, which is naturally connected to the concept of volume minimization in computational geometry. Theoretically, we introduce a new set of geometric conditions for topic model identifiability, which are weaker than conventional separability conditions relying on the existence of anchor words or pure topic documents. We conduct finite-sample error analysis for the proposed estimator and discuss the connection of our results with existing ones. We conclude with empirical studies on both simulated and real datasets.

We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al., 2019)--a large-scale crowd-sourced fantasy text adventure game wherein an agent perceives and interacts with the world through textual natural language. Goals in this environment take the form of character-based quests, consisting of personas and motivations. We augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of steadily increasing difficulty for training agents to achieve such goals. In particular, we measure curriculum difficulty in terms of the rarity of the quest in the original training distribution--an easier environment is one that is more likely to have been found in the unaugmented dataset. An ablation study shows that this method of learning from the tail of a distribution results in significantly higher generalization abilities as measured by zeroshot performance on never-before-seen quests. Figure 1: The LIGHT questing environment presented as a 2 player game deployed in Messenger.