Engineers are torn between an attitude of strong design and dreams of autonomous devices. They want full mastery of their artifacts while wishing these were much more adaptive or ‘‘intelligent.’’ Today, while we must still spoon-feed (program, repair, upgrade) our most sophisticated computer and robotic systems, insatiable demand for novelty has created an escalation in system size and complexi...

We present an approach for smoothing treebank-PCFG lexicons by interpolating treebank lexical parameter estimates with estimates obtained from unannotated data via the Inside-outside algorithm. The PCFG has complex lexical categories, making relative-frequency estimates from a treebank very sparse. This kind of smoothing for complex lexical categories results in improved parsing performance, wi...

The paper discusses the architecture and development of an Argument Workbench, which supports an analyst in reconstructing arguments from across textual sources. The workbench takes a semi-automated, interactive approach searching in a corpus for fine-grained argument elements, which are concepts and conceptual patterns in expressions that are associated with argumentation schemes. The expressi...

A central goal of algorithmic research is to determine how fast computational problems can be solved in the worst case. Theorems from complexity theory state that there are problems that, on inputs of size n, can be solved in t(n) time but not in t(n)1− time for > 0. The main challenge is to determine where in this hierarchy various natural and important problems lie. Throughout the years, many...

Journaling has been a popular reliability tool for file systems. However, journaling may involve writing updates twice, once to the journal, and once to potentially random update locations. The journal granularity tends to be coarse, leading to more bytes written than necessary. We introduce Fine-grained Journal Store (FJS). Finegrained Journal Store uses the journal as the final storage locati...

Traditionally, concurrent data structures are protected by a single mutual exclusion lock so that only one thread may access the data structure at any time. This coarse-grained approach makes it relatively easy to reason about correctness, but it severely limits parallelism. More advanced algorithms instead perform synchronisation at a finer grain. They employ sophisticated synchronisation sche...

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, beginning with fine-grained categorization on the Stanford Dogs data set. In this work we use an RNN of the same structure but substitute a more powerful visual network and perform large-scale pre-training of the visual network outside of the...