Tourism in India plays a quintessential role in the country's economy with an estimated 9.2% GDP share for the year 2018. With a yearly growth rate of 6.2%, the industry holds a huge potential for being the primary driver of the economy as observed in the nations of the Middle East like the United Arab Emirates. The historical and cultural diversity exhibited throughout the geography of the nation is a unique spectacle for people around the world and therefore serves to attract tourists in tens of millions in number every year. Traditionally, tour guides or academic professionals who study these heritage monuments were responsible for providing information to the visitors regarding their architectural and historical significance. However, unfortunately this system has several caveats when considered on a large scale such as unavailability of sufficient trained people, lack of accurate information, failure to convey the richness of details in an attractive format etc. Recently, machine learning approaches revolving around the usage of monument pictures have been shown to be useful for rudimentary analysis of heritage sights. This paper serves as a survey of the research endeavors undertaken in this direction which would eventually provide insights for building an automated decision system that could be utilized to make the experience of tourism in India more modernized for visitors.

Multimodal deep learning systems which employ multiple modalities like text, image, audio, video, etc., are showing better performance in comparison with individual modalities (i.e., unimodal) systems. Multimodal machine learning involves multiple aspects: representation, translation, alignment, fusion, and co-learning. In the current state of multimodal machine learning, the assumptions are that all modalities are present, aligned, and noiseless during training and testing time. However, in real-world tasks, typically, it is observed that one or more modalities are missing, noisy, lacking annotated data, have unreliable labels, and are scarce in training or testing and or both. This challenge is addressed by a learning paradigm called multimodal co-learning. The modeling of a (resource-poor) modality is aided by exploiting knowledge from another (resource-rich) modality using transfer of knowledge between modalities, including their representations and predictive models. Co-learning being an emerging area, there are no dedicated reviews explicitly focusing on all challenges addressed by co-learning. To that end, in this work, we provide a comprehensive survey on the emerging area of multimodal co-learning that has not been explored in its entirety yet. We review implementations that overcome one or more co-learning challenges without explicitly considering them as co-learning challenges. We present the comprehensive taxonomy of multimodal co-learning based on the challenges addressed by co-learning and associated implementations. The various techniques employed to include the latest ones are reviewed along with some of the applications and datasets. Our final goal is to discuss challenges and perspectives along with the important ideas and directions for future work that we hope to be beneficial for the entire research community focusing on this exciting domain.

Throw out the chalk and blackboards, because there's a new player in the world of education. While ink and copybooks were the foundation stones for a new era of learning centuries ago, in 2021 we stand on the precipice of another massive change in educational technology: artificial intelligence. Today's Daily Dose takes you through the exciting new ways technology is set to mold education in the years to come. We look at how it can ease stress, save time and put a 21st-century touch on some age-old teaching methods. So hang up your backpack and put away your pencil and scissors.

My wife and I were recently driving in Virginia, amazed yet again that the GPS technology on our phones could guide us through a thicket of highways, around road accidents, and toward our precise destination. The artificial intelligence (AI) behind the soothing voice telling us where to turn has replaced passenger-seat navigators, maps, even traffic updates on the radio. How on earth did we survive before this technology arrived in our lives? We survived, of course, but were quite literally lost some of the time. My reverie was interrupted by a toll booth. It was empty, as were all the other booths at this particular toll plaza.

EDITOR'S NOTE: This article originally appeared at TomDispatch.com. To stay on top of important articles like these, sign up to receive the latest updates from TomDispatch.com. By signing up, you confirm that you are over the age of 16 and agree to receive occasional promotional offers for programs that support The Nation's journalism. You can read our Privacy Policy here. By signing up, you confirm that you are over the age of 16 and agree to receive occasional promotional offers for programs that support The Nation's journalism. You can read our Privacy Policy here.

AI in medicine, particular in pediatric medicine holds much promise in taking scarce human expertise and making it available throughout rural America and to the rest of the world. Rwanda has one pediatric cardiologist in the country. In 2015, when neural network technology succeeded in building computer algorithms which were better than humans at image recognition signaled the beginning of this renaissance in AI. But, as the above chart courtesy of Jeff Dean, head of Google Brain shows, the only way to get increasing degrees of accuracy is to have more and more data. Any of you in major metro areas will see Waymo vans driving around collecting more and more data to feed autonomous driving software development.

Embeddings of high-dimensional data are widely used to explore data, to verify analysis results, and to communicate information. Their explanation, in particular with respect to the input attributes, is often difficult. With linear projects like PCA the axes can still be annotated meaningfully. With non-linear projections this is no longer possible and alternative strategies such as attribute-based color coding are required. In this paper, we review existing augmentation techniques and discuss their limitations. We present the Non-Linear Embeddings Surveyor (NoLiES) that combines a novel augmentation strategy for projected data (rangesets) with interactive analysis in a small multiples setting. Rangesets use a set-based visualization approach for binned attribute values that enable the user to quickly observe structure and detect outliers. We detail the link between algebraic topology and rangesets and demonstrate the utility of NoLiES in case studies with various challenges (complex attribute value distribution, many attributes, many data points) and a real-world application to understand latent features of matrix completion in thermodynamics.

Multimodal sentiment analysis aims to extract and integrate semantic information collected from multiple modalities to recognize the expressed emotions and sentiment in multimodal data. This research area's major concern lies in developing an extraordinary fusion scheme that can extract and integrate key information from various modalities. However, one issue that may restrict previous work to achieve a higher level is the lack of proper modeling for the dynamics of the competition between the independence and relevance among modalities, which could deteriorate fusion outcomes by causing the collapse of modality-specific feature space or introducing extra noise. To mitigate this, we propose the Bi-Bimodal Fusion Network (BBFN), a novel end-to-end network that performs fusion (relevance increment) and separation (difference increment) on pairwise modality representations. The two parts are trained simultaneously such that the combat between them is simulated. The model takes two bimodal pairs as input due to the known information imbalance among modalities. In addition, we leverage a gated control mechanism in the Transformer architecture to further improve the final output. Experimental results on three datasets (CMU-MOSI, CMU-MOSEI, and UR-FUNNY) verifies that our model significantly outperforms the SOTA. The implementation of this work is available at https://github.com/declare-lab/BBFN.

Several approaches have been developed to answer specific questions that a user may have about an AI system that can plan and act. However, the problems of identifying which questions to ask and that of computing a user-interpretable symbolic description of the overall capabilities of the system have remained largely unaddressed. This paper presents an approach for addressing these problems by learning user-interpretable symbolic descriptions of the limits and capabilities of a black-box AI system using low-level simulators. It uses a hierarchical active querying paradigm to generate questions and to learn a user-interpretable model of the AI system based on its responses. In contrast to prior work, we consider settings where imprecision of the user's conceptual vocabulary precludes a direct expression of the agent's capabilities. Furthermore, our approach does not require assumptions about the internal design of the target AI system or about the methods that it may use to compute or learn task solutions. Empirical evaluation on several game-based simulator domains shows that this approach can efficiently learn symbolic models of AI systems that use a deterministic black-box policy in fully observable scenarios.

This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P(y|x), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a template into a textual string prompt x' that has some unfilled slots, and then the language model is used to probabilistically fill the unfilled information to obtain a final string x, from which the final output y can be derived. This framework is powerful and attractive for a number of reasons: it allows the language model to be pre-trained on massive amounts of raw text, and by defining a new prompting function the model is able to perform few-shot or even zero-shot learning, adapting to new scenarios with few or no labeled data. In this paper we introduce the basics of this promising paradigm, describe a unified set of mathematical notations that can cover a wide variety of existing work, and organize existing work along several dimensions, e.g.the choice of pre-trained models, prompts, and tuning strategies. To make the field more accessible to interested beginners, we not only make a systematic review of existing works and a highly structured typology of prompt-based concepts, but also release other resources, e.g., a website http://pretrain.nlpedia.ai/ including constantly-updated survey, and paperlist.