Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items are scored independently by their similarity to the query in the latent embedding space. The structure of the ranked list (i.e. considering the set of items returned as a whole) is not taken into account. This can be a problem because the set of top predictions can be either too diverse (contain results that contradict each other) or are not diverse enough. In this paper we introduce a method for learning latent structured rankings that improves over existing methods by providing the right blend of predictions at the top of the ranked list. Particular emphasis is put on making this method scalable. Empirical results on large scale image annotation and music recommendation tasks show improvements over existing approaches.

Previous work on recommender systems mainly focus on fitting the ratings provided by users. However, the response patterns, i.e., some items are rated while others not, are generally ignored. We argue that failing to observe such response patterns can lead to biased parameter estimation and sub-optimal model performance. Although several pieces of work have tried to model users' response patterns, they miss the effectiveness and interpretability of the successful matrix factorization collaborative filtering approaches. To bridge the gap, in this paper, we unify explicit response models and PMF to establish the Response Aware Probabilistic Matrix Factorization (RAPMF) framework. We show that RAPMF subsumes PMF as a special case. Empirically we demonstrate the merits of RAPMF from various aspects.

This paper considers stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms. In this setting, after pulling an arm i, the decision maker also observes the rewards for some other actions related to i. We will see that this model is suited to content recommendation in social networks, where users' reactions may be endorsed or not by their friends. We provide efficient algorithms based on upper confidence bounds (UCBs) to leverage this additional information and derive new bounds improving on standard regret guarantees. We also evaluate these policies in the context of movie recommendation in social networks: experiments on real datasets show substantial learning rate speedups ranging from 2.2x to 14x on dense networks.

Automated sports commentary is a form of automated narrative. Sports commentary exists to keep the viewer informed and entertained. One way to entertain the viewer is by telling brief stories relevant to the game in progress. We introduce a system called the Sports Commentary Recommendation System (SCoReS) that can automatically suggest stories for commentators to tell during games. Through several user studies, we compared commentary using SCoReS to three other types of commentary and show that SCoReS adds significantly to the broadcast across several enjoyment metrics. We also collected interview data from professional sports commentators who positively evaluated a demonstration of the system. We conclude that SCoReS can be a useful broadcast tool, effective at selecting stories that add to the enjoyment and watchability of sports. SCoReS is a step toward automating sports commentary and, thus, automating narrative.

Autonomous aesthetic evaluation is the Holy Grail of generative music, and one of the great challenges of computational creativity. Unlike most other computational activities, there is no notion of optimality in evaluating creative output: there are subjective impressions involved, and framing obviously plays a big role. When developing metacreative systems, a purely objective fitness function is not available: the designer is thus faced with how much of their own aesthetic to include. Can a generative system be free of the designer’s bias? This paper presents a system that incorporates an aesthetic selection process that allows for both human-designed and non-human fitness functions.

We describe ANGELINA3, a system that can automatically develop games along a defined theme, by selecting appropriate multimedia content from a variety of sources and incorporating it into a game's design. We discuss these capabilities in the context of the FACE model for assessing progress in the building of creative systems, and discuss how ANGELINA3 can be improved through further work.

This demonstration presents MaestroGenesis, a program that helps users create complete polyphonic musical pieces from as little as a simple, human composed monophonic melody. MaestroGenesis creates music by exploiting two key ideas behind the functional scaffolding for musical composition (FSMC) approach: (1) that music a function of time and (2) that functional transformations of initial human starting melodies, or scaffolds, inherit some of the essential human qualities contained in the scaffold. Music in FSMC is represented as a functional relationship between the scaffold and a generated accompaniment. The GUI helps users evolve these functions by importing and developing their music through a breeding process akin to animal breeding, called interactive evolutionary computation. Some resulting pieces are indistinguishable from completely human-composed pieces.

Most systems for generating cinematic shot sequences for virtual environments focus on the low-level problems of camera placement. While this approach will create a sequence of camera shots which film individual events in a virtual environment, it does not account for the high-level effects shot sequences have on viewer inferences. There are systems which are based on well known cinematography principles such as the rule of thirds and other framing principals, however these usually utilize schemas or predefined shots and do not reason about the high level cognitive effects on the viewer. In this paper a system is proposed which can reason directly about these high-level cognitive and narrative effects of a shot sequence on the viewer’s mental state.

Xa-lan is a computer program written in Common-LISP to generate music scores with a high level of notational/symbolic expressivity. Generation is driven by audio-analysis of melodic profiles. Once a melodic contour is input to the software, graphic transformations of the original profile stochastically control the different notational elements of the score. The Xa-lan routines display their final output using the ‘Expressive Notation Package’ of PWGL, a LISP-based visual composition environment. A full range of traditional and non-conventional music notation elements can be algorithmically generated with Xa-lan, retrieving to the user a ‘ready-to-play’ or fully ex-pressive music score.

In the proposed demo we will present a method for design of musical composition using the Audio Oracle (AO) - a machine improvisation method that constructs and produces variation from a music recording using a graph of repeated factors found in the recording. The compositional / improvisation use of AO involves controlling the rate of recombination, the length of common history (length of the repeated factors) and selection of regions in the AO where the machine operates. One of the challenges in working with AO is understanding the generative potential of different audio materials and marking and allocating regions in a recording where AO should operate to achieve the desired musical result. Recently we introduced a novel analysis method "on top" of the AO structure that captures aspects of order and complexity that we call Information Rate. This measure, belonging broadly to a field of study know as Musical Information Dynamics, is related to Bense formulation of aesthetics in terms of entropy and compression. In the demo we will briefly explain the theory behind Audio Oracle and Information Rate and demonstrate a process of designing a composition / structured improvisation based on analysis of the AO graph. In contrast to the usual live interaction method where both the audio input to the oracle and the improvisation are done "on the fly", in this presentation the audio analysis will be done prior to the presentation, while during the talk we will show the process of planning a composition and then do a live performance with the AO based on this design.