The present paper details the process followed for creating training and test corpora for a dependency parser generator (Maltparser). The starting point is the Cast3LB corpus, which contains constituency analyses of Spanish texts. These constituency analyses are automatically transformed into dependency analyses. In addition, the empirically and semiautomatically obtention of a set of syntactic...

Dependency parsers are among the most crucial tools in natural language processing as they have many important applications in downstream tasks such as information retrieval, machine translation and knowledge acquisition. We introduce the Yara Parser, a fast and accurate open-source dependency parser based on the arc-eager algorithm and beam search. It achieves an unlabeled accuracy of 93.32 on...

In this paper, we present a framework for multi-lingual dependency parsing. Our bottom-up deterministic parser adopts Nivre’s algorithm (Nivre, 2004) with a preprocessor. Support Vector Machines (SVMs) are utilized to determine the word dependency attachments. Then, a maximum entropy method (MaxEnt) is used for determining the label of the dependency relation. To improve the performance of the ...

We present a self-training approach to unsupervised dependency parsing that reuses existing supervised and unsupervised parsing algorithms. Our approach, called ‘iterated reranking’ (IR), starts with dependency trees generated by an unsupervised parser, and iteratively improves these trees using the richer probability models used in supervised parsing that are in turn trained on these trees. Ou...

This paper describes research in improving DGP (Dependency Graph Parser). DGP is one of the most efficient dependency parser for Polish today. However, it is non-deterministic which makes it insufficient when numerous graphs are proposed for one sentence. In our research we aim to overcome this problem by adding weights to grammar rules and thus making possible to rank the output trees and choo...

This paper describes a system developed for the transformation of English sentences into a first order logical form representation. The metho dology is centered on the use of a dependency grammar based parser . We demonstrate the suitability of applying a dependency parser based solution to the given task and in turn explain some of the limitations and challenges involved when using such an app...

We adapt the greedy stack LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles (Goldberg and Nivre, 2013) instead of assuming an error-free action history. This form of training, which accounts for model predictions at training time, improves parsing accuracies. We discuss some modifications needed in order to get training with expl...

We describe a method for enriching the output of a parser with information available in a corpus. The method is based on graph rewriting using memorybased learning, applied to dependency structures. This general framework allows us to accurately recover both grammatical and semantic information as well as non-local dependencies. It also facilitates dependency-based evaluation of phrase structur...

We present a statistical post-editing method for modifying the dependency labels in a dependency analysis. We test the method using two English datasets, three parsing systems and three labelled dependency schemes. We demonstrate how it can be used both to improve dependency label accuracy in parser output and highlight problems with and differences between constituency-to-dependency conversions.

In this paper we introduce a new approach to transition-based dependency parsing. We propose that the parser construct an undirected graph during the parsing process, instead of a standard directed dependency structure. A posteriori, the output undirected structure is converted into a dependency tree. This alleviates error propagation, a characteristic problem of these systems. We apply this ap...