David Leo Wright Hall

Less Grammar, More Features

We present a parser that relies primarily on extracting information directly from surface spans rather than on propagating information through enriched grammar structure. For example, instead of creating separate grammar symbols to mark the definiteness of an NP, our parser might instead capture the same information from the first word of the NP. Moving context out of the grammar and onto surface features can greatly simplify the structural component of the parser: because so many deep syntactic cues have surface reflexes, our system can still parse accurately with context-free backbones as minimal as Xbar grammars. Keeping the structural backbone simple and moving features to the surface also allows easy adaptation to new languages and even to new tasks. On the SPMRL 2013 multilingual constituency parsing shared task (Seddah et al., 2013), our system outperforms the top single parser system of Bjorkelund et al. (2013) on a range of languages. In addition, despite being designed for syntactic analysis, our system also achieves stateof-the-art numbers on the structural sentiment task of Socher et al. (2013). Finally, we show that, in both syntactic parsing and sentiment analysis, many broad linguistic trends can be captured via surface features.

Sparser, Better, Faster GPU Parsing

Due to their origin in computer graphics, graphics processing units (GPUs) are highly optimized for dense problems, where the exact same operation is applied repeatedly to all data points. Natural language processing algorithms, on the other hand, are traditionally constructed in ways that exploit structural sparsity. Recently, Canny et al. (2013) presented an approach to GPU parsing that sacrifices traditional sparsity in exchange for raw computational power, obtaining a system that can compute Viterbi parses for a high-quality grammar at about 164 sentences per second on a mid-range GPU. In this work, we reintroduce sparsity to GPU parsing by adapting a coarse-to-fine pruning approach to the constraints of a GPU. The resulting system is capable of computing over 404 Viterbi parses per second—more than a 2x speedup—on the same hardware. Moreover, our approach allows us to efficiently implement less GPU-friendly minimum Bayes risk inference, improving throughput for this more accurate algorithm from only 32 sentences per second unpruned to over 190 sentences per second using pruning—nearly a 6x speedup.

Rockingham Forest, Northamptonshire: The Evolution of a Landscape

Abstract The Rockingham Forest Project created detailed digital mapping, from archaeological fieldwork, historic map, and aerial photographic evidence, to chart the evolution over the last millennium of the landscape of the greater part of the medieval Forest of Rockingham, Northamptonshire. It has revealed a landscape where the physical geography, especially the geology acting via the soils, was the primary determinant of land use, but where the administrative units, particularly the townships, controlled how land-use change was structured. The townships were typically self-contained units combining a balance of resources, with adjacent townships often following quite different trajectories, sometimes for hundreds of years. This landscape appears to have been extensively replanned in the late Anglo-Saxon and early medieval periods; saw continuing settlement expansion and sometimes extensive woodland clearance until the early fourteenth century; then in the late medieval and post-medieval periods experienced a growing rate of reorganisation through enclosure, reaching its height during Parliamentary enclosure in the eighteenth and nineteenth centuries. Throughout this period woodland was in decline, though at greatly varying rates, until by the twentieth century it had been totally destroyed as a distinctive landscape zone. The process has been one of the progressive decoupling of land use from physical geography, most intensively during the last 150 years with processes such as rapid urbanisation and mineral extraction, creating a wholly new landscape.