This paper compares three different types of representations that resolve long-distance dependency into binary representation as it is required in PCFG parsing. Each conversion is applied to the German TIGER Treebank in the PCFG parsing experiments. The examination of data and the labeled depen-dency evaluation show that the choice of conversion of treebank data in the preprocessing step can influence the F-score up to 2.83 % and that each con-version has its own advantages and limits. The result of this paper shows that this preprocessing step is not trivial in parsing free word order languages.
Traditionally, deep, wide-coverage linguistic resources are hand-crafted and their creation is time-...
International audienceThe article introduces novel instanciations of three French constituent treeba...
We suggest a new annotation scheme for unlexicalized PCFGs that is inspired by formal language theor...
Proceedings of the Ninth International Workshop on Treebanks and Linguistic Theories. Editors: Mar...
This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impa...
Statistical parsers are effective but are typically limited to producing projective dependencies or ...
Statistical parsers are e ective but are typically limited to producing projective dependencies or c...
This paper shows how finite approximations of long distance dependency (LDD) resolution can be obtai...
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by...
This paper presents a comparative study of probabilistic treebank parsing of Ger-man, using the Negr...
We present an approach for smoothing treebank-PCFG lexicons by interpolating treebank lexical parame...
Statistical parsers are e ective but are typically limited to producing projective dependencies or c...
This paper describes a parser which generates parse trees with empty elements in which traces and fi...
Recent advances in parsing technology have made treebank parsing with discontinuous constituents p...
This paper presents empirical studies and closely corresponding theoretical models of the performanc...
Traditionally, deep, wide-coverage linguistic resources are hand-crafted and their creation is time-...
International audienceThe article introduces novel instanciations of three French constituent treeba...
We suggest a new annotation scheme for unlexicalized PCFGs that is inspired by formal language theor...
Proceedings of the Ninth International Workshop on Treebanks and Linguistic Theories. Editors: Mar...
This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impa...
Statistical parsers are effective but are typically limited to producing projective dependencies or ...
Statistical parsers are e ective but are typically limited to producing projective dependencies or c...
This paper shows how finite approximations of long distance dependency (LDD) resolution can be obtai...
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by...
This paper presents a comparative study of probabilistic treebank parsing of Ger-man, using the Negr...
We present an approach for smoothing treebank-PCFG lexicons by interpolating treebank lexical parame...
Statistical parsers are e ective but are typically limited to producing projective dependencies or c...
This paper describes a parser which generates parse trees with empty elements in which traces and fi...
Recent advances in parsing technology have made treebank parsing with discontinuous constituents p...
This paper presents empirical studies and closely corresponding theoretical models of the performanc...
Traditionally, deep, wide-coverage linguistic resources are hand-crafted and their creation is time-...
International audienceThe article introduces novel instanciations of three French constituent treeba...
We suggest a new annotation scheme for unlexicalized PCFGs that is inspired by formal language theor...