Take a look at the Universal Dependencies v1 documentation for a detailed description of the v1 representation, its set of relations, and links to dependency treebank downloads. You might also want to look at the the current v2 Universal Dependencies documentationbut we have yet to update our tools to this representation.
More information on the Universal Dependencies converter and the enhanced representation can be found in this paper. If you have an English constituency treebank in Penn Treebank s-expression format in the file or directory treebankyou can use our code to convert it to a file of basic Universal Dependencies in CoNLL-U format with this command: To output relations in the original Stanford Dependencies representation use the -originalDependencies option when running the parser or the -parse.
If you are using the Neural Network dependency parser and to get the original Stanford Dependencies, you have to use the model trained on a corpus annotated with the Stanford Dependencies representation using the following option:.
The dependency code is part of the Stanford parser.
Go here to download a version. About Stanford dependencies provides a representation of grammatical relations between words in a sentence. They have been designed to be easily understood and effectively used by people who want to extract textual relations. Stanford dependencies SD are triplets: The standard dependencies for the sentence Bills on ports and immigration were submitted by Senator Brownback, Republican of Kansas are given below, as well as two graphical representations: We manually annotatedwords with SD for English.
The effort is meant to address the scarcity of both gold standard dependency corpora for English and annotated resources for parsing web test.
This resource is described here: This annotation effort has led to refinements of Stanford Dependencies. We describe changes to the standard and propose analyses for a few syntactic constructions of interest, to be found in the following paper:.
We are now primarily working on "Penn treebank parser online dating" improved taxonomy to capture grammatical relations across languages, including morphologically rich ones.
A first version of this new standard, called Universal Dependencies, is described here: A more recent version of Universal Dependencies is described in the following two papers: A Multilingual Treebank Collection.
Sebastian Schuster and Christopher D. Enhanced English Universal Dependencies: The most up to date version of Universal Depencies is documented online at http: All details about the English dependencies can be found in the manual: Marie-Catherine de Marneffe and Christopher D. The manual contains a description of all the existing English grammatical relations in the representation.
It explains the differences between the five types of representation available, and how such types of representation can be obtained. It also gives references to further discussion and use of the Stanford dependencies.
The definition of the set of dependencies has evolved a little over the years, and the particular patterns used to convert phrase structure trees to dependencies have been improved quite a bit. Hence, if you are publishing a paper using Stanford Dependencies, we really appreciate it if you could indicate precisely which version you are using. This is easily done by citing the version of the Stanford Parser code used.
In practice, the dependencies can be obtained using our software in two ways. Either by using the Stanford parser with the -outputFormat typedDependencies option on raw text, or directly on phrase-structure trees using the EnglishGrammaticalStructure class available in the parser package.
If you have an English constituency treebank in Penn Treebank s-expression format in the file or directory treebankyou can use our code to convert it to a file of basic Stanford Dependencies in CoNLL-X format with this command: The default representation is the "CCprocessed" one, which collapses and propagates dependencies as shown in Figure 1, in contrast to Figure 2, which shows the "basic" dependencies, which are not collapsed nor propagated.
For more details, refer to section 5 of the Stanford Dependencies manual. Only the required WSJ set were hand-verified; the representations in
Penn treebank parser online dating other two sets were automatically generated. A corpus of English biomedical texts, with hand-corrected annotations in a slight variant of the Stanford typed dependency format is available The BioInfer project.
Stanford dependencies are also available for Chinese. A brief description of the Chinese grammatical relations can be found in this paper. There is now a multi-site effort to produce dependency treebanks over a broad range of languages adopting a compatible dependency taxonomy.
While the original and canonical approach to generating the Stanford Dependencies is using the Stanford parser, there are now many other parsers which produce them, which may offer better speed or precision. Any phrase structure parser that constructs PTB style trees can be used, in addition to any trainable dependency parser.
When using an alternative phrase structure parser, the Stanford Parser class EnglishGrammaticalStructure is used to extract dependencies from the resulting
Penn treebank parser online dating parse trees.
Trainable dependency parsers can produce the basic Stanford Dependency representation. This is a projective variant of the Stanford Dependencies that can be transformed into the default representation, CCprocessed, using EnglishGrammaticalStructure.
The table below summarizes some methods for generating the Stanford Dependencies along with the speed and accuracy of each approach on section 22 of the Penn TreeBank. Links are provided to the corresponding software packages and trained parsing models some of the dependency models were trained by us.