Intelligent text entry systems, including the now-ubiquitous predictive keyboard, can make text entry more efficient, but little is known about how these systems affect the content that people write. To study how predictive text systems affect content, we compared image captions written with different kinds of predictive text suggestions. Our key findings were that captions written with suggestions were shorter and that they included fewer words that that the system did not predict. Suggestions also boosted text entry speed, but with diminishing benefit for faster typists. Our findings imply that text entry systems should be evaluated not just by speed and accuracy but also by their effect on the content written.

A system capable of suggesting multi-word phrases while someone is writing could supply ideas about content and phrasing and allow those ideas to be inserted efficiently. Meanwhile, statistical language modeling has provided various approaches to predicting phrases that users type. We introduce a simple extension to the familiar mobile keyboard suggestion interface that presents phrase suggestions that can be accepted by a repeated-tap gesture. In an extended composition task, we found that phrases were interpreted as suggestions that affected the content of what participants wrote more than conventional single-word suggestions, which were interpreted as predictions. We highlight a design challenge: how can a phrase suggestion system make valuable suggestions rather than just accurate predictions'

A growing number of large collaborative idea generation platforms promise that by generating ideas together, people can create better ideas than any would have alone. But how might these platforms best leverage the number and diversity of contributors to help each contributor generate even better ideas? Prior research suggests that seeing particularly creative or diverse ideas from others can inspire you, but few scalable mechanisms exist to assess diversity. We contribute a new scalable crowd-powered method for evaluating the diversity of sets of ideas. The method relies on similarity comparisons (is idea A more similar to B or C) generated by non-experts to create an abstract spatial idea map. Our validation study reveals that human raters agree with the estimates of dissimilarity derived from our idea map as much or more than they agree with each other. People seeing the diverse sets of examples from our idea map generate more diverse ideas than those seeing randomly selected examples. Our results also corroborate findings from prior research showing that people presented with creative examples generated more creative ideas than those who saw a set of random examples. We see this work as a step toward building more effective online systems for supporting large scale collective ideation.

Typical synthesizers only provide controls to the low-level parameters of sound-synthesis, such as wave-shapes or filter envelopes. In contrast, composers often want to adjust and express higher-level qualities, such as how "scary" or "steady" sounds are perceived to be. We develop a system which allows users to directly control abstract, high-level qualities of sounds. To do this, our system learns functions that map from synthesizer control settings to perceived levels of high-level qualities. Given these functions, our system can generate high-level knobs that directly adjust sounds to have more or less of those qualities. We model the functions mapping from control-parameters to the degree of each high-level quality using Gaussian processes, a nonparametric Bayesian model. These models can adjust to the complexity of the function being learned, account for nonlinear interaction between control-parameters, and allow us to characterize the uncertainty about the functions being learned. By tracking uncertainty about the functions being learned, we can use active learning to quickly calibrate the tool, by querying the user about the sounds the system expects to most improve its performance. We show through simulations that this model-based active learning approach learns high-level knobs on certain classes of target concepts faster than several baselines, and give examples of the resulting automatically- constructed knobs which adjust levels of non-linear, high- level concepts.

We propose a new way to raise the level of discourse in the programming process: permit ambiguity, but manage it by linking it to unambiguous examples. This allows programming environments to work with high-level descriptions that lack precise semantics, such as natural language descriptions or conceptual diagrams, without requiring programmers to formulate their ideas in a formal language first. As an example of this idea, we present Zones, a code search and reuse interface that connects code with ambiguous natural language annotations about its purpose. The backend, called ProcedureSpace, induces relationships between these purpose annotations, static code analysis features, and a variety of natural language background knowledge. ProcedureSpace can search for code given purpose descriptions or vice versa, and can even find code that was never annotated or commented. Since completed Zones searches become annotations, the system learns from user interaction. Users in a preliminary study found that reasoning jointly over natural language and programming language helped them reuse code.

We present a game-based interface for acquiring common sense knowledge. In addition to being interactive and entertaining, our interface guides the knowledge acquisition process to learn about the most salient characteristics of a particular concept. We use statistical classification methods to discover the most informative characteristics in the Open Mind Common Sense knowledge base, and use these characteristics to play a game of 20 Questions with the user. Our interface also allows users to enter knowledge more quickly than a more traditional knowledge-acquisition interface. An evaluation showed that users enjoyed the game and that it increased the speed of knowledge acquisition.