A Declarative Formalism for Constituent-to-Dependency Conversion
نویسندگان
چکیده
In this paper, we present a declarative formalism for writing rule sets to convert constituent trees into dependency graphs. The formalism is designed to be independent of the annotation scheme and provides a highly task-related syntax, abstracting away from the underlying graph data structures. We have implemented the formalism in our search tool and used a preliminary version to create a rule set that converts more than 97% of the TIGER corpus.
منابع مشابه
Language Independent Dependency to Constituent Tree Conversion
We present a dependency to constituent tree conversion technique that aims to improve constituent parsing accuracies by leveraging dependency treebanks available in a wide variety in many languages. The technique works in two steps. First, a partial constituent tree is derived from a dependency tree with a very simple deterministic algorithm that is both language and dependency type independent...
متن کاملFrom Dependencies to Constituents in the Reference Corpus for the Processing of Basque (EPEC)
In this paper the process for turning a dependency-based corpus to a constituentbased one is explained. For this purpose, first both the Dependency and the Constituent formalism are analized and then the corresponding equivalences of linguistic phenomena are treated. This process has had different phases in which the linguistic equivalences have been improved. Finally, the evaluation process is...
متن کاملComputational Aspects of Non-Projective Dependency Grammars
Lexicalised Configuration Grammars (lcg) is a declarative framework for non-projective dependency grammars. Lexical entries in lcg are local well-formedness conditions for drawings (trees equipped with a total order). The framework is powerful enough to encode a large number of existing grammar formalisms declaratively. The expressivity of lcg, however, comes at the cost of np-complete word pro...
متن کاملتبدیل خودکار درخت‌بانک وابستگی فارسی به درخت‌بانک سازه‌ای
There are two major types of treebanks: dependency-based and constituency-based. Both of them have applications in natural language processing and computational linguistics. Several dependency treebanks have been developed for Persian. However, there is no available big size constituency treebank for this language. In this paper, we aim to propose an algorithm for automatic conversion of a depe...
متن کاملDown-stream effects of tree-to-dependency conversions
Dependency analysis relies on morphosyntactic evidence, as well as semantic evidence. In some cases, however, morphosyntactic evidence seems to be in conflict with semantic evidence. For this reason dependency grammar theories, annotation guidelines and tree-to-dependency conversion schemes often differ in how they analyze various syntactic constructions. Most experiments for which constituent-...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009