The Web is a huge repository; this is particularly true for mathematical knowledge. Sophisticated search capabilities for mathematical Web resources are required by research and education. We are working on the integration of classifiers for mathematical Web content into a working instance of a Web indexing framework. It is a natural choice to reuse a computer algebra system for the actual clas...

We provide a new weighted parsing algorithm for deterministic context free grammar parsing inspired by LR (Knuth, 1965). The parser is weighted by a discriminative model that allows determinism (Collins, 2002). We show that the discriminative model allows to take advantage of morphological information available in the data, hence allowing to achieve state of the art results both in time and in ...

We introduce a new method for incremental shift-reduce parsing of discontinuous constituency trees, based on the fact that discontinuous trees can be transformed into continuous trees by changing the order of the terminal nodes. It allows for a clean formulation of different oracles, leads to faster parsers and provides better results. Our best system achieves an F1 of 80.02 on TIGER.

Shift-reduce parsing has been studied extensively for diverse grammars due to the simplicity and running efficiency. However, in the field of constituency parsing, shift-reduce parsers lag behind state-of-the-art parsers. In this paper we propose a semi-supervised approach for advancing shift-reduce constituency parsing. First, we apply the uptraining approach (Petrov, S. et al. 2010. In Procee...

Simple Recurrent Networks (SRNs) have been widely used in natural language processing tasks. However, their ability to handle long-term dependencies between sentence constituents is somewhat limited. NARX networks have recently been shown to outperform SRNs by preserving past information in explicit delays from the network’s prior output. However, it is unclear how the number of delays should b...

Quantifier elimination (QE) is a powerful tool for problem solving. Once a problem is expressed as a formula, such a method converts it to a simpler, quantifier-free equivalent, thus solving the problem. Particularly many problems live in the domain of real numbers, which makes real QE very interesting. Among the so far implemented methods, QE by cylindrical algebraic decomposition (CAD) is the...

Simple Recurrent Networks (SRNs) have been widely used in natural language tasks. SARDSRN extends the SRN by explicitly representing the input sequence in a SARDNET self-organizing map. The distributed SRN component leads to good generalization and robust cognitive properties, whereas the SARDNET map provides exact representations of the sentence constituents. This combination allows SARDSRN to...

The foundations of the symmetry approach to the classification problem ofintegrable non-linear evolution systems are briefly described. Within the framework of the symmetry approach the ten-parametric family of the third order non-linear evolution coupled KdV-like systems is investigated. The necessary integrability conditions lead to an over-determined non-linear algebraic system. To solve tha...

We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores. The shift-reduce parsing model eschews lexical information entirely, and uses only the 1-best supertags to parse a sentence, providing furt...