The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the probing framework and perform a comparative probing study of static (GloVe) and contextual (BERT) embeddings. Our experiments indicate that both encode some idiomatic information to varying degrees, but yield conflicting evidence as to whether idiomaticity is encoded in the vector norm, leaving this an open question. We also identify some limitations of the used dataset and highlight important directions for future work in improving its suitability for a probing analysis.

Modelling taxonomic and thematic relatedness is important for building AI with comprehensive natural language understanding. The goal of this paper is to learn more about how taxonomic information is structurally encoded in embeddings. To do this, we design a new hypernym-hyponym probing task and perform a comparative probing study of taxonomic and thematic SGNS and GloVe embeddings. Our experiments indicate that both types of embeddings encode some taxonomic information, but the amount, as well as the geometric properties of the encodings, are independently related to both the encoder architecture, as well as the embedding training data. Specifically, we find that only taxonomic embeddings carry taxonomic information in their norm, which is determined by the underlying distribution in the data.

Creating a vaccine involves examining the structure of the virus and identifying its spike protein which is used to gain entry to the host's cells. Antibodies that target the spike protein can block the virus and inhibit replication. In the case of the Covid-19 virus, the genetic sequence of the virus was released in January 2020 to allow developers around the world to have a blueprint for their research. Typically, drugs are developed by pharmaceutical companies analysing chemical compounds to assess properties in a drug, for example absorption rates, metabolic stability, binding strengths and so forth. Today's commercially available anti-viral therapeutics target diseases like influenza, hepatitis C, chickenpox, papilloma and AIDS and the R&D activities to model properties for future anti-viral therapeutics are a significant part of the typical $2.5 billion cost of a new drug.

Machine learning is often used to build predictive models by extracting patterns from large datasets. These models are used in predictive data analytics applications including price prediction, risk assessment, predicting customer behavior, and document classification. This introductory textbook offers a detailed and focused treatment of the most important machine learning approaches used in predictive data analytics, covering both theoretical concepts and practical applications. Technical and mathematical material is augmented with explanatory worked examples, and case studies illustrate the application of these models in the broader business context. This second edition covers recent developments in machine learning, especially in a new chapter on deep learning, and two new chapters that go beyond predictive analytics to cover unsupervised learning and reinforcement learning.

The helpful person guiding you through your online purchase might not be a person at all. As artificial intelligence and natural language processing advance, we often don't know if we are talking to a person or an AI-powered chatbot, says Tom Kelleher, Ph.D., an advertising professor in the University of Florida's College of Journalism and Communications. What matters more than who (or what) is on the other side of the chat, Kelleher has found, is the perceived humanness of the interaction. With text-based bots becoming ubiquitous and AI-powered voice systems emerging, consumers of everything from shoes to insurance may find themselves talking to non-humans. Companies will have to decide when bots are appropriate and effective and when they're not.

The helpful person guiding you through your online purchase might not be a person at all. As artificial intelligence and natural language processing advance, we often don't know if we are talking to a person or an AI-powered chatbot, says Tom Kelleher, Ph.D., an advertising professor in the University of Florida's College of Journalism and Communications. What matters more than who (or what) is on the other side of the chat, Kelleher has found, is the perceived humanness of the interaction. With text-based bots becoming ubiquitous and AI-powered voice systems emerging, consumers of everything from shoes to insurance may find themselves talking to non-humans. Companies will have to decide when bots are appropriate and effective and when they're not.

Deep learning is an artificial intelligence technology that enables computer vision, speech recognition in mobile phones, machine translation, AI games, driverless cars, and other applications. When we use consumer products from Google, Microsoft, Facebook, Apple, or Baidu, we are often interacting with a deep learning system. In this volume in the MIT Press Essential Knowledge series, computer scientist John Kelleher offers an accessible and concise but comprehensive introduction to the fundamental technology at the heart of the artificial intelligence revolution. Kelleher explains that deep learning enables data-driven decisions by identifying and extracting patterns from large datasets; its ability to learn from complex data makes deep learning ideally suited to take advantage of the rapid growth in big data and computational power. Kelleher also explains some of the basic concepts in deep learning, presents a history of advances in the field, and discusses the current state of the art.

This paper 1 connects a series of papers dealing with taxonomic word embeddings. It begins by noting that there are different types of semantic relatedness and that different lexical representations encode different forms of relatedness. A particularly important distinction within semantic relatedness is that of thematic versus taxonomic relatedness. Next, we present a number of experiments that analyse taxonomic embeddings that have been trained on a synthetic corpus that has been generated via a random walk over a taxonomy. These experiments demonstrate how the properties of the synthetic corpus, such as the percentage of rare words, are affected by the shape of the knowledge graph the corpus is generated from. Finally, we explore the interactions between the relative sizes of natural and synthetic corpora on the performance of embeddings when taxonomic and thematic embeddings are combined.

This paper examines to what degree current deep learning architectures for image caption generation capture spatial language. On the basis of the evaluation of examples of generated captions from the literature we argue that systems capture what objects are in the image data but not where these objects are located: the captions generated by these systems are the output of a language model conditioned on the output of an object detector that cannot capture fine-grained location information. Although language models provide useful knowledge for image captions, we argue that deep learning image captioning architectures should also model geometric relations between objects.

Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we argue that deep neural networks incorporate both perspectives and, furthermore, that leveraging this aspect of deep learning may help in solving complex problems within language technology, such as modelling language and perception in the domain of spatial cognition.