Peripheral displays are useful for organizing information and providing additional screen space for managing information. One design issue is whether peripheral displays should be part of a single large contiguous display space or segmented into many dedicated displays. To test this, an experiment was conducted comparing performance for on-screen versus off-screen displays and bordered (i.e., w...

Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and d...

Sequences found at the beginning of TV shows help the audience absorb the essence of previous episodes, and grab their attention with upcoming plots. In this paper, we propose a novel task, text recap extraction. Compared with conventional summarization, text recap extraction captures the duality of summarization and plot contingency between adjacent episodes. We present a new dataset, TVRecap,...

Tools for visualizing and creating groundtruth and metadata are crucial for document image analysis research. In this paper, we describe TrueViz which is a tool for visualizing and editing groundtruth/metadata for OCR. TrueViz is implemented in the Java programming language and works on various platforms including Windows and Unix. TrueViz reads and stores groundtruth/metadata in XML format, an...

Effective authoring aids, whether for novice, secondlanguage, or experienced writers, require linguistic knowledge. With respect to depth of analysis, authoring aids that aim to support revising and editing go beyond POS-tagging but cannot work on complete, mostly well-formed sentences to perform deep syntactic analysis, since a text undergoing revision is in a constant state of flux. In order ...

Ranking text documents given a query is one of the key tasks in information retrieval. Typical solutions include classical vector space models using weighted word counts and the cosine similarity (TFIDF) with no machine learning at all, or Latent Semantic Indexing (LSI) using unsupervised learning to learn a low dimensional space of “latent concepts” via a reconstruction objective. The former a...

We describe a system, G2A, that produces ACT-R models from GOMS models containing hierarchical methods, visual and memory stores, and control constructs. Because GOMS is a more abstract formalism than ACT-R, a single GOMS operator might be plausibly translated in different ways into ACT-R productions (e.g., a GOMS Look-for operator might be carried out by different visual search strategies in A...

We present a text-based tool for editing talking-head video that enables an iterative workflow. On each iteration users can edit the wording of speech, further refine mouth motions if necessary to reduce artifacts, and manipulate non-verbal aspects performance by inserting gestures (e.g., smile) or changing overall style energetic, mumble). Our requires only 2 3 minutes target actor it synthesi...

We describe a system, G2A, that produces ACT-R models from GOMS models containing hierarchical methods, visual and memory stores, and control constructs. Because GOMS is a more abstract formalism than ACT-R, a single GOMS operator might be plausibly translated in different ways into ACT-R productions (e.g., a GOMS Look-for operator might be carried out by different visual search strategies in A...