The recognition of multiword expressions (MWEs) in a sentence is important for such linguistic analyses as syntactic and semantic parsing, because it is known that combining an MWE into a single token improves accuracy for various NLP tasks, such as dependency parsing and constituency parsing. However, MWEs are not annotated in Penn Treebank. Furthermore, when converting word-based dependency t...

We propose a system to carry out the joint parsing of syntactic and semantic dependencies in multiple languages for our participation in the shared task of CoNLL-2009. We present an iterative approach for dependency parsing and semantic role labeling. We have participated in the closed challenge, and our system achieves 73.98% on labeled macro F1 for the complete problem, 77.11% on labeled atta...

We present a dependency parser for Persian, called ParsPer, developed using the graph-based parser in the Mate Tools. The parser is trained on the entire Uppsala Persian Dependency Treebank with a specific configuration that was selected by MaltParser as the best performing parsing representation. The treebank’s syntactic annotation scheme is based on Stanford Typed Dependencies with extensions...

We report on the recent development of ParZu, a German dependency parser. We discuss the effect of POS tagging and morphological analysis on parsing performance, and present novel ways of improving performance of the components, including the use of morphological features for POS-tagging, the use of syntactic information to select good POS sequences from an n-best list, and using parsed text as...

Recent parsing research has started addressing the questions a) how parsers trained on different syntactic resources differ in their performance and b) how to conduct a meaningful evaluation of the parsing results across such a range of syntactic representations. Two German treebanks, Negra and TüBa-D/Z, constitute an interesting testing ground for such research given that the two treebanks mak...

We report an empirical study on the role of syntactic features in building a semisupervised named entity (NE) tagger. Our study addresses two questions: What types of syntactic features are suitable for extracting potential NEs to train a classifier in a semi-supervised setting? How good is the resulting NE classifier on testing instances dissimilar from its training data? Our study shows that ...

The Norwegian Dependency Treebank is a new syntactic treebank for Norwegian Bokmål and Nynorsk with manual syntactic and morphological annotation, developed at the National Library of Norway in collaboration with the University of Oslo. It is the first publically available treebank for Norwegian. This paper presents the core principles behind the syntactic annotation and how these principles we...

Deterministic dependency parsing is a robust and efficient approach to syntactic parsing of unrestricted natural language text. In this paper, we analyze its potential for incremental processing and conclude that strict incrementality is not achievable within this framework. However, we also show that it is possible to minimize the number of structures that require nonincremental processing by ...

We compare the performance of a transition-based parser in regards to different annotation schemes. We propose to convert some specific syntactic constructions observed in the universal dependency treebanks into a so-called more standard representation and to evaluate parsing performances over all the languages of the project. We show that the “standard” constructions do not lead systematically...

Exact parsing with finite state automata is deemed inappropriate because of the unbounded non-locality languages overwhelmingly exhibit. We propose a way to structure the parsing task in order to make it amenable to local classification methods. This allows us to build a Dynamic Bayesian Network which uncovers the syntactic dependency structure of English sentences. Experiments with the Wall St...