Dependency structure provides grammatical relations between words, which have shown to be effective in Statistical Machine Translation (SMT). In this paper, we present an open source module in Moses which implements a dependency-to-string model. We propose a method to transform the input dependency tree into a corresponding constituent tree for reusing the tree-based decoder in Moses. In our ex...

We evaluated the conservation attitudes of the local villagers living adjacent to the Kalakad-Mundanthurai Tiger Reserve in southern India 6 years after implementation of a World Bank funded eco-development project. We assessed attitudes towards three facets of conservation: the tiger, an emblematic species signifying India's commitment to wildlife conservation; the forest, a principle source o...

Dependency measures are fundamental for a number of important applications in data mining and machine learning. They are ubiquitously used: for feature selection, for clustering comparisons and validation, as splitting criteria in random forest, and to infer biological networks, to list a few. More generally, there are three important applications of dependency measures: detection, quantificati...

We participated in the OLYMPICS task in IWSLT 2012 and submitted two formal runs using a forest-to-string translation system. Our primary run achieved better translation quality than our contrastive run, but worse than a phrase-based and a hierarchical system using Moses.

In this article we illustrate how fine-grained longitudinal analyses of land holding and land use among forest peasant households in an Amazonian village can enrich our understanding of the poverty/land cover nexus. We examine the dynamic links in shifting cultivation systems among asset poverty, land use, and land cover in a community where poverty is persistent and primary forests have been r...

We introduce a broad family of decision trees, Composite Trees, whose leaf classifiers are selected out of a hypothesis set composed of p subfamilies with different complexities. We prove new data-dependent learning guarantees for this family in the multi-class setting. These learning bounds provide a quantitative guidance for the choice of the hypotheses at each leaf. Remarkably, they depend o...

Different from traditional active learning based on sentence-wise full annotation (FA), this paper proposes active learning with dependency-wise partial annotation (PA) as a finer-grained unit for dependency parsing. At each iteration, we select a few most uncertain words from an unlabeled data pool, manually annotate their syntactic heads, and add the partial trees into labeled data for parser...

We describe “treeblazing”, a method of using annotations from the GENIA treebank to constrain a parse forest from an HPSG parser. Combining this with self-training, we show significant dependency score improvements in a task of adaptation to the biomedical domain, reducing error rate by 9% compared to out-of-domain gold data and 6% compared to self-training. We also demonstrate improvements in ...

The dependency of many African rural households on natural resources for sustenance is widely acknowledged. The utilization and commercialization of indigenous fruit trees (IFTs) has in the past been overlooked by extension agencies due to the misconception that they do not play a major role in contributing to the rural livelihoods. There is new and increasing emphasis on the contribution of in...