Modern machine learning algorithms are capable of providing remarkably accurate point-predictions; however, questions remain about their statistical reliability. Unlike conventional machine learning methods, conformal prediction algorithms return confidence sets (i.e., set-valued predictions) that correspond to a given significance level. Moreover, these confidence sets are valid in the sense that they guarantee finite sample control over type 1 error probabilities, allowing the practitioner to choose an acceptable error rate. In our paper, we propose inductive conformal prediction (ICP) algorithms for the tasks of text infilling and part-of-speech (POS) prediction for natural language data. We construct new conformal prediction-enhanced bidirectional encoder representations from transformers (BERT) and bidirectional long short-term memory (BiLSTM) algorithms for POS tagging and a new conformal prediction-enhanced BERT algorithm for text infilling. We analyze the performance of the algorithms in simulations using the Brown Corpus, which contains over 57,000 sentences. Our results demonstrate that the ICP algorithms are able to produce valid set-valued predictions that are small enough to be applicable in real-world applications. We also provide a real data example for how our proposed set-valued predictions can improve machine generated audio transcriptions.

Peer assessment systems are emerging in many social and multi-agent settings, such as peer grading in large (online) classes, peer review in conferences, peer art evaluation, etc. However, peer assessments might not be as accurate as expert evaluations, thus rendering these systems unreliable. The reliability of peer assessment systems is influenced by various factors such as assessment ability of peers, their strategic assessment behaviors, and the peer assessment setup (e.g., peer evaluating group work or individual work of others). In this work, we first model peer assessment as multi-relational weighted networks that can express a variety of peer assessment setups, plus capture conflicts of interest and strategic behaviors. Leveraging our peer assessment network model, we introduce a graph convolutional network which can learn assessment patterns and user behaviors to more accurately predict expert evaluations. Our extensive experiments on real and synthetic datasets demonstrate the efficacy of our proposed approach, which outperforms existing peer assessment methods.

A robot chef named Flippy, designed to cook 300 burgers a day, has been upgraded and can now also fill up baskets of fries and place them in the deep fat fryer. Built by Miso Robotics, a food services startup from Pasadena, California, it is now capable of working an entire fry station and can do twice as many food preparation jobs as the first Flippy, including basket filling, emptying, and returning. White Castle has partnered with Miso on the Flippy project, giving feedback that has allowed the startup to improve the functionality of the product. They deployed the original Flippy to a location in the Chicagoland area in September 2020. Automatic Dispenser for high volume foods: New Automatic Dispenser options make Flippy 2 autonomous.

Billionaire VC Tim Draper (via Draper Associates) has led a $6 million Series A in wellness tracking startup, Vivoo. Also participating in the funding round is ONCE Ventures, Revo Capital, 500 Startups (which backed its pre-seed), Global Ventures, and (the female-led consumer tech startup focused) Halogen Ventures. The personalized nutrition and lifestyle startup sells subscription-based at-home urine test kits that work in conjunction with an app. Its machine learning technology remotely analyzes a user's peed-on test strip to serve up custom'wellness' insights, then and there, offering recommendations across a range of areas such as nutrition and biological function. The startup's founding team is led by CEO and co-founder Miray Tayfun, a serial founder and bioengineer by background who graduated from Stanford's postgraduate programs.

This is a fast-changing and critical time for Earth Observation (EO), especially for those involved in its use for climate and meteorology. On this course, you'll get a comprehensive overview of the Copernicus Programme and the wealth of EO data it provides, as well as how AI and ML are transforming the interpretation of EO data. You'll learn about the Copernicus data and services and the massive amounts of Earth observation data that are collected every day from space, covering the oceans, land, atmosphere and, over longer periods, the climate. You'll then learn basic AI and ML concepts and types, exploring how they have transformed many aspects of the EO'value chain'. This includes automatic feature extraction, new ways of processing very large data sets, and the development of new products and services.

Let's be honest, it's been a rough decade at this point, and things seem to be getting worse rather than better. Online radicalization has seen many of the world's political systems spin out of control to the point of uselessness. Climate change is a problem facing literally all of us that few in power seem interested in addressing. And our economic situation seems to be predicated on everyone buying lots of stuff all the time, despite the fact that most of the cost of living is swallowed up by housing. It's a lot, and things can feel generally very bleak right now.

Prompt-learning has become a new paradigm in modern natural language processing, which directly adapts pre-trained language models (PLMs) to $cloze$-style prediction, autoregressive modeling, or sequence to sequence generation, resulting in promising performances on various tasks. However, no standard implementation framework of prompt-learning is proposed yet, and most existing prompt-learning codebases, often unregulated, only provide limited implementations for specific scenarios. Since there are many details such as templating strategy, initializing strategy, and verbalizing strategy, etc. need to be considered in prompt-learning, practitioners face impediments to quickly adapting the desired prompt learning methods to their applications. In this paper, we present {OpenPrompt}, a unified easy-to-use toolkit to conduct prompt-learning over PLMs. OpenPrompt is a research-friendly framework that is equipped with efficiency, modularity, and extendibility, and its combinability allows the freedom to combine different PLMs, task formats, and prompting modules in a unified paradigm. Users could expediently deploy prompt-learning frameworks and evaluate the generalization of them on different NLP tasks without constraints. OpenPrompt is publicly released at {\url{ https://github.com/thunlp/OpenPrompt}}.

Planning the layout of bicycle-sharing stations is a complex process, especially in cities where bicycle sharing systems are just being implemented. Urban planners often have to make a lot of estimates based on both publicly available data and privately provided data from the administration and then use the Location-Allocation model popular in the field. Many municipalities in smaller cities may have difficulty hiring specialists to carry out such planning. This thesis proposes a new solution to streamline and facilitate the process of such planning by using spatial embedding methods. Based only on publicly available data from OpenStreetMap, and station layouts from 34 cities in Europe, a method has been developed to divide cities into micro-regions using the Uber H3 discrete global grid system and to indicate regions where it is worth placing a station based on existing systems in different cities using transfer learning. The result of the work is a mechanism to support planners in their decision making when planning a station layout with a choice of reference cities.

Recently, the speech community is seeing a significant trend of moving from deep neural network based hybrid modeling to end-to-end (E2E) modeling for automatic speech recognition (ASR). While E2E models achieve the state-of-the-art results in most benchmarks in terms of ASR accuracy, hybrid models are still used in a large proportion of commercial ASR systems at the current time. There are lots of practical factors that affect the production model deployment decision. Traditional hybrid models, being optimized for production for decades, are usually good at these factors. Without providing excellent solutions to all these factors, it is hard for E2E models to be widely commercialized. In this paper, we will overview the recent advances in E2E models, focusing on technologies addressing those challenges from the industry's perspective.

In recent years, low-resource Machine Reading Comprehension (MRC) has made significant progress, with models getting remarkable performance on various language datasets. However, none of these models have been customized for the Urdu language. This work explores the semi-automated creation of the Urdu Question Answering Dataset (UQuAD1.0) by combining machine-translated SQuAD with human-generated samples derived from Wikipedia articles and Urdu RC worksheets from Cambridge O-level books. UQuAD1.0 is a large-scale Urdu dataset intended for extractive machine reading comprehension tasks consisting of 49k question Answers pairs in question, passage, and answer format. In UQuAD1.0, 45000 pairs of QA were generated by machine translation of the original SQuAD1.0 and approximately 4000 pairs via crowdsourcing. In this study, we used two types of MRC models: rule-based baseline and advanced Transformer-based models. However, we have discovered that the latter outperforms the others; thus, we have decided to concentrate solely on Transformer-based architectures. Using XLMRoBERTa and multi-lingual BERT, we acquire an F1 score of 0.66 and 0.63, respectively.