Recently, these has been a surge on studying how to obtain partially annotated data for model supervision. However, there still lacks a systematic study on how to train statistical models with partial annotation (PA). Taking dependency parsing as our case study, this paper describes and compares two straightforward approaches for three mainstream dependency parsers. The first approach is previo...

We give the complete picture of the complexity of conjunctive query answering under (weakly-)(frontier-)guarded disjunctive existential rules, i.e., existential rules extended with disjunction, and their main subclasses, linear rules and inclusion dependencies.

We give an algorithm for constructing the algebraic hull of a given matrix Lie algebra. It is based on an algorithm for finding integral linear dependencies of the roots of a polynomial, that is probably of independent interest.

in this paper the density and temperature dependencies of surface tension are investigated. using the lennard-jones (12,6), as an effective pair interaction potential, a linear expression is derived for isotherms of g /r2  versus r2 for some normal and chlorofluorocarbons (cfcs) fluids, where  is surface tension and r = 1/v is molar density. the linearity behavior of the derived equation is wel...

The recent introduction of task dependencies in the OpenMP specification provides new ways of synchronizing tasks. Application programmers can now describe the data a task will read as input and write as output, letting the runtime system resolve fine-grain dependencies between tasks to decide which task should execute next. Such an approach should scale better than the excessive global synchro...

Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length. We show the training of RNNs with only linear sequential dependencies can be parallelized over the sequence length using the parallel scan algorithm, leading to rapid training on long sequences even with small ...

Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length. We show the training of RNNs with only linear sequential dependencies can be parallelized over the sequence length using the parallel scan algorithm, leading to rapid training on long sequences even with small ...

Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suita...