We present "Treebank Refinement", which is a method that tunes the representation of syntactic analyses in a treebank to the specific needs of probabilistic context-free grammar (PCFG) parsers. We show that the choice of representations of syntactic analyses in a treebank determines the performance of PCFG parsers but is rarely chosen to satisfy their specific needs. Their known weakness to model contextual information can be alleviated by choosing representations that introduce more contextual information into node labels. Treebank Refinement defines a function that selects and modifies node labels in the original representation that lack this kind of contextual information. From a more general point of view, the success of this method...
Abstract. Although state-of-the-art parsers for natural language are lexicalized, it was recently sh...
Proceedings of the Sixth International Workshop on Treebanks and Linguistic Theories. Editors: Ko...
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage g...
We present "Treebank Refinement", which is a method that tunes the representation of syntactic analy...
Treebanks are a valuable resource for the training of parsers that perform automatic annotation of u...
The development of frameworks that allow to state grammars for natural languages in a mathematically...
This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra...
The linguistic annotation of a treebank conforms to an annotation scheme, which has to serve several...
We present the Modified French Treebank (MFT), a completely revamped French Treebank, derived from t...
Proceedings of the Ninth International Workshop on Treebanks and Linguistic Theories. Editors: Mar...
In the last decade, the Penn treebank has become the standard data set for evaluating parsers. The f...
The purpose of this paper is to describe the TüBa-D/Z treebank of written German and to compare it t...
Recent years have seen an increasing interest in developing standards for linguistic annotation, wit...
This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impa...
This paper profiles significant differences in syntactic distribution and differences in word class ...
Abstract. Although state-of-the-art parsers for natural language are lexicalized, it was recently sh...
Proceedings of the Sixth International Workshop on Treebanks and Linguistic Theories. Editors: Ko...
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage g...
We present "Treebank Refinement", which is a method that tunes the representation of syntactic analy...
Treebanks are a valuable resource for the training of parsers that perform automatic annotation of u...
The development of frameworks that allow to state grammars for natural languages in a mathematically...
This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra...
The linguistic annotation of a treebank conforms to an annotation scheme, which has to serve several...
We present the Modified French Treebank (MFT), a completely revamped French Treebank, derived from t...
Proceedings of the Ninth International Workshop on Treebanks and Linguistic Theories. Editors: Mar...
In the last decade, the Penn treebank has become the standard data set for evaluating parsers. The f...
The purpose of this paper is to describe the TüBa-D/Z treebank of written German and to compare it t...
Recent years have seen an increasing interest in developing standards for linguistic annotation, wit...
This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impa...
This paper profiles significant differences in syntactic distribution and differences in word class ...
Abstract. Although state-of-the-art parsers for natural language are lexicalized, it was recently sh...
Proceedings of the Sixth International Workshop on Treebanks and Linguistic Theories. Editors: Ko...
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage g...