Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community. and suggest future directions.

However, the first machine learning libraries as we know them today, which provide tools and frameworks for implementing and training machine learning models, did not appear until the 1980s and 1990s. One of the earliest machine learning libraries was the Statlib library, which was developed at Carnegie Mellon University in the 1980s. This library provided tools for statistical analysis and machine learning, including support for decision trees and neural networks. Other early machine learning libraries include the Weka library, developed at the University of Waikato in New Zealand in the 1990s, and the LIBSVM library developed at the National Taiwan University in the late 1990s. These libraries provided tools for a variety of machine learning tasks, including classification, regression, and clustering.

Melbourne – Visually impaired student Adam Whitehead has long relied on a computer and assistive technology to help him read course materials and take exams at the University of Melbourne in Australia. He has watched with concern as universities in Australia and beyond move to crack down on ChatGPT -- a free program that generates original text about virtually any subject in response to a prompt -- over fears of cheating. As the chatbot stirs debate over the use of technology and artificial intelligence (AI) in education, disabled students and educators have said the benefits should not be overlooked in a rush to regulate. This could be due to a conflict with your ad-blocking or security software. Please add japantimes.co.jp and piano.io to your list of allowed sites.

I'm a full stack developer of most things computer sciency and academic with a true passion for teaching. I've been teaching others about games development, programming, computer graphics, animation and web design for over 25 years in universities in Australia and Europe at the full professor level. I've also consulted for Unity, SAE, the Australian Institute of Entertainment and Wikitude. My best selling textbooks including Holistic Game Development with Unity are used in over 100 institutions world-wide. My graduates work at companies like Apple, Ubisoft, LinkedIn and Deloitte Digital.

Writing with next-phrase suggestions powered by large language models is becoming more pervasive by the day. However, research to understand writers' interaction and decision-making processes while engaging with such systems is still emerging. We conducted a qualitative study to shed light on writers' cognitive processes while writing with next-phrase suggestion systems. To do so, we recruited 14 amateur writers to write two reviews each, one without suggestions and one with suggestions. Additionally, we also positively and negatively biased the suggestion system to get a diverse range of instances where writers' opinions and the bias in the language model align or misalign to varying degrees. We found that writers interact with next-phrase suggestions in various complex ways: Writers abstracted and extracted multiple parts of the suggestions and incorporated them within their writing, even when they disagreed with the suggestion as a whole; along with evaluating the suggestions on various criteria. The suggestion system also had various effects on the writing process, such as altering the writer's usual writing plans, leading to higher levels of distraction etc. Based on our qualitative analysis using the cognitive process model of writing by Hayes as a lens, we propose a theoretical model of 'writer-suggestion interaction' for writing with GPT-2 (and causal language models in general) for a movie review writing task, followed by directions for future research and design.

English news headlines form a register with unique syntactic properties that have been documented in linguistics literature since the 1930s. However, headlines have received surprisingly little attention from the NLP syntactic parsing community. We aim to bridge this gap by providing the first news headline corpus of Universal Dependencies annotated syntactic dependency trees, which enables us to evaluate existing state-of-the-art dependency parsers on news headlines. To improve English news headline parsing accuracies, we develop a projection method to bootstrap silver training data from unlabeled news headline-article lead sentence pairs. Models trained on silver headline parses demonstrate significant improvements in performance over models trained solely on gold-annotated long-form texts. Ultimately, we find that, although projected silver training data improves parser performance across different news outlets, the improvement is moderated by constructions idiosyncratic to outlet.

Large collections of time series data are commonly organized into structures with different levels of aggregation; examples include product and geographical groupings. It is often important to ensure that the forecasts are coherent so that the predicted values at disaggregate levels add up to the aggregate forecast. The growing interest of the Machine Learning community in hierarchical forecasting systems indicates that we are in a propitious moment to ensure that scientific endeavors are grounded on sound baselines. For this reason, we put forward the HierarchicalForecast library, which contains preprocessed publicly available datasets, evaluation metrics, and a compiled set of statistical baseline models. Our Python-based reference framework aims to bridge the gap between statistical and econometric modeling, and Machine Learning forecasting research.

The brains of all bilaterally symmetric animals on Earth are divided into left and right hemispheres. The anatomy and functionality of the hemispheres have a large degree of overlap, but there are asymmetries and they specialize to possess different attributes. Several studies have used computational models to mimic hemispheric asymmetries with a focus on reproducing human data on semantic and visual processing tasks. In this study, we aimed to understand how dual hemispheres could interact in a given task. We propose a bilateral artificial neural network that imitates a lateralization observed in nature: that the left hemisphere specializes in specificity and the right in generalities. We used two ResNet-9 convolutional neural networks with different training objectives and tested it on an image classification task. Our analysis found that the hemispheres represent complementary features that are exploited by a network head which implements a type of weighted attention. The bilateral architecture outperformed a range of baselines of similar representational capacity that don't exploit differential specialization. The results demonstrate the efficacy of bilateralism, contribute to an understanding of bilateralism in biological brains and the architecture serves as an inductive bias when designing new AI systems.

Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-stationarity). In this work, we take the first steps towards the fundamental challenge of on-policy and off-policy evaluation amidst structured changes due to active, passive, or hybrid non-stationarity. Towards this goal, we make a higher-order stationarity assumption such that non-stationarity results in changes over time, but the way changes happen is fixed. We propose, OPEN, an algorithm that uses a double application of counterfactual reasoning and a novel importance-weighted instrument-variable regression to obtain both a lower bias and a lower variance estimate of the structure in the changes of a policy's past performances. Finally, we show promising results on how OPEN can be used to predict future performances for several domains inspired by real-world applications that exhibit non-stationarity.

Trajectory prediction in a cluttered environment is key to many important robotics tasks such as autonomous navigation. However, there are an infinite number of possible trajectories to consider. To simplify the space of trajectories under consideration, we utilise homotopy classes to partition the space into countably many mathematically equivalent classes. All members within a class demonstrate identical high-level motion with respect to the environment, i.e., travelling above or below an obstacle. This allows high-level prediction of a trajectory in terms of a sparse label identifying its homotopy class. We therefore present a light-weight learning framework based on variable-order Markov processes to learn and predict homotopy classes and thus high-level agent motion. By informing a Gaussian Mixture Model (GMM) with our homotopy class predictions, we see great improvements in low-level trajectory prediction compared to a naive GMM on a real dataset.