This article describes the process of designing a point-and-click adventure game that aimed at using dream logic as the basis to create its narrative puzzles. The technical solution to tackle this challenge was using Procedural Content Generation (PCG) as the design approach, which was used expressively to recreate the instability and changeability of dreams. Although PCG brought about replayability to the game, called Symon, it also created a series of other development problems, which had to be remedied through other design devices. One of the lessons learned during the development of the game is that PCG is not a blanket solution to problems, but rather an expressive tool to be used in combination to other design strategies; human factors are also key both during the development and reception of narrative video games.

As a story unfolds, it constructs a depiction of events, and at the same time, it also builds conceptual structure at a higher, interpretive level. This higher-level structure provides the terms for understanding the unfolding story, indicating what kinds of features and consequences characterize it – a story ontology . The process by which a tale constructs a story ontology is not straightforward, and in many ways is just as complex as the action at the event level. It involves an interaction between inferred situations and contexts, each with their own networks of terms and structures, which jostle for dominance. I refer to this interaction as governance . In this work, I demonstrate an example of governance at both levels, using a scene from the series Game of Thrones . When the interpretive terms of a story emerge, an understanding of what kinds of events might come next – the possible causal implications – are also conveyed, even if they are unexpected.

Wikipedia provides an enormous amount of background knowledge to reason about the semantic relatedness between two entities. We propose Wikipedia-based Distributional Semantics for Entity Relatedness (DiSER), which represents the semantics of an entity by its distribution in the high dimensional concept space derived from Wikipedia. DiSER measures the semantic relatedness between two entities by quantifying the distance between the corresponding high-dimensional vectors. DiSER builds the model by taking the annotated entities only, therefore it improves over existing approaches, which do not distinguish between an entity and its surface form. We evaluate the approach on a benchmark that contains the relative entity relatedness scores for 420 entity pairs. Our approach improves the accuracy by 12% on state of the art methods for computing entity relatedness. We also show an evaluation of DiSER in the Entity Disambiguation task on a dataset of 50 sentences with highly ambiguous entity mentions. It shows an improvement of 10% in precision over the best performing methods. In order to provide the resource that can be used to find out all the related entities for a given entity, a graph is constructed, where the nodes represent Wikipedia entities and the relatedness scores are reflected by the edges. Wikipedia contains more than 4.1 millions entities, which required efficient computation of the relatedness scores between the corresponding 17 trillions of entity-pairs.

Motivated by generating personalized recommendations using ordinal (or preference) data, we study the question of learning a mixture of MultiNomial Logit (MNL) model, a parameterized class of distributions over permutations, from partial ordinal or preference data (e.g. pair-wise comparisons). Despite its long standing importance across disciplines including social choice, operations research and revenue management, little is known about this question. In case of single MNL models (no mixture), computationally and statistically tractable learning from pair-wise comparisons is feasible. However, even learning mixture with two MNL components is infeasible in general. Given this state of affairs, we seek conditions under which it is feasible to learn the mixture model in both computationally and statistically efficient manner. We present a sufficient condition as well as an efficient algorithm for learning mixed MNL models from partial preferences/comparisons data. In particular, a mixture of $r$ MNL components over $n$ objects can be learnt using samples whose size scales polynomially in $n$ and $r$ (concretely, $r^{3.5}n^3(log n)^4$, with $r\ll n^{2/7}$ when the model parameters are sufficiently incoherent). The algorithm has two phases: first, learn the pair-wise marginals for each component using tensor decomposition; second, learn the model parameters for each component using Rank Centrality introduced by Negahban et al. In the process of proving these results, we obtain a generalization of existing analysis for tensor decomposition to a more realistic regime where only partial information about each sample is available.

Crowdsourcing is a popular paradigm for effectively collecting labels at low cost. The Dawid-Skene estimator has been widely used for inferring the true labels from the noisy labels provided by non-expert crowdsourcing workers. However, since the estimator maximizes a non-convex log-likelihood function, it is hard to theoretically justify its performance. In this paper, we propose a two-stage efficient algorithm for multi-class crowd labeling problems. The first stage uses the spectral method to obtain an initial estimate of parameters. Then the second stage refines the estimation by optimizing the objective function of the Dawid-Skene estimator via the EM algorithm. We show that our algorithm achieves the optimal convergence rate up to a logarithmic factor. We conduct extensive experiments on synthetic and real datasets. Experimental results demonstrate that the proposed algorithm is comparable to the most accurate empirical approach, while outperforming several other recently proposed methods.

Psychologists and social scientists have been researching creativity in humans for several years, and it has gained the attention of artificial intelligence and robotics researchers as well. In this abstract, we discuss the emotional and conversational interface required for a humanoid robot to socially interact with children in order to learn new creative concepts. We briefly describe the approach we are taking to develop such a humanoid robot that can collaborate with children to discover creative concepts.

We give an overview of how the CADENCE architecture addresses the problem of turn-taking in embodied interaction.

Important aspects of human cognition, like creativity and play, involve dealing with multiple divergent views of objects, goals, and plans. We argue in this paper that the current model of optimization that drives much of modern machine learning research is far too restrictive a paradigm to mathematically model the richness of human cognition. Instead, we propose a much more flexible and powerful framework of equilibration, which not only generalizes optimization, but also captures a rich variety of other problems, from game theory, complementarity problems, network equilibrium problems in economics, and equation solving. Our thesis is that creative activity involves dealing not with a single objective function, which optimization requires, but rather balancing multiple divergent and possibly contradictory goals. Such modes of cognition are better modeled using the framework of variational inequalities (VIs). We provide a brief review of this paradigm for readers unfamiliar with the underlying mathematics, and sketch out how VIs can account for creativity and play in human and animal cognition.

AI has a long history of making fine tools, and an equally long history of trying to simulate human intelligence, without, I contend, really understanding what intelligence consists in: the ability to deal with the world, which presupposes having a stake in one's own being. The tools are very nifty, but I don't see how it is even possible to simulate having a stake in one's own being.

Connecting the dots between discoveries in neuroscience(neuroplasticity), psychoneuroimmunology(the brain-immune loop) and user experience (gadget rub-off) indicate the nature of our time spent with gadgets is a vector in human health - mentally, socially and physically. The positive design of our interactions with devices therefore can have a positive impact on economy, civilization and society. Likewise, the absence of design that encourages positive interaction may encourage undesirable behaviors. Much like the architecture of physical spaces and buildings, the consequences of the architecture of the 21stcentury conversation between man and machine may last generations. AI and the Internet of Things are primary vectors for positive and negative impacts of technology.  We describe a growing body of co-discoveries occurring across a variety of disciplines that support the argument for human sciences in technology design.