Sökning: "Dependency parsing"

Visar resultat 1 - 5 av 15 avhandlingar innehållade orden Dependency parsing.

1. 1. Inductive Dependency Parsing of Natural Language Text

   Författare :Joakim Nivre; Walter Daelemans; Växjö universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; natural language parsing; dependency parsing; memory-based learning; treebank parsing; Systems engineering; Systemteknik; Computer and Information Sciences Computer Science; Data- och informationsvetenskap;

   Sammanfattning : This thesis investigates new methods for syntactic parsing of unrestricted natural language text under requirements of robustness and disambiguation. A parsing system is required to assign to every sentence in a text at least one analysis (robustness) and at most one analysis (disambiguation). LÄS MER

3. 2. Tree Transformations in Inductive Dependency Parsing

   Författare :Jens Nilsson; Joakim Nivre; Pierre Nugues; Växjö universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Inductive Dependency Parsing; Dependency Structure; Tree Transformation; Non-projectivity; Coordination; Verb Group; Language technology; Språkteknologi; Computer and Information Sciences Computer Science; Data- och informationsvetenskap;

   Sammanfattning : This licentiate thesis deals with automatic syntactic analysis, or parsing, of natural languages. A parser constructs the syntactic analysis, which it learns by looking at correctly analyzed sentences, known as training data. The general topic concerns manipulations of the training data in order to improve the parsing accuracy. LÄS MER

4. 3. Tree Transformations in Inductive Dependency Parsing

   Författare :Jens Nilsson; Joakim Nivre; Pierre Nugues; Växjö universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Inductive Dependency Parsing; Dependency Structure; Tree Transformation; Non-projectivity; Coordination; Verb Group; Language technology; Språkteknologi; Computer and Information Sciences Computer Science; Data- och informationsvetenskap;

   Sammanfattning : This licentiate thesis deals with automatic syntactic analysis, or parsing, of natural languages. A parser constructs the syntactic analysis, which it learns by looking at correctly analyzed sentences, known as training data. The general topic concerns manipulations of the training data in order to improve the parsing accuracy. LÄS MER

5. 4. Transition-Based Natural Language Parsing with Dependency and Constituency Representations

   Författare :Johan Hall; Joakim Nivre; Welf Löwe; Sandra Kübler; Växjö universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Natural Language Parsing; Syntactic Parsing; Dependency Structure; Phrase Structure; Machine Learning; Computer science; Datavetenskap; Computer and Information Sciences Computer Science; Data- och informationsvetenskap;

   Sammanfattning : Denna doktorsavhandling undersöker olika aspekter av automatisk syntaktisk analys av texter på naturligt språk. En parser eller syntaktisk analysator, som vi definierar den i denna avhandling, har till uppgift att skapa en syntaktisk analys för varje mening i en text på naturligt språk. LÄS MER

7. 5. MaltParser -- An Architecture for Inductive Labeled Dependency Parsing

   Författare :Johan Hall; Joakim Nivre; Welf Löwe; Martin Volk; Växjö universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Dependency Parsing; Support Vector Machines; Machine Learning; Language technology; Språkteknologi; Computer and Information Sciences Computer Science; Data- och informationsvetenskap;

   Sammanfattning : This licentiate thesis presents a software architecture for inductive labeled dependency parsing of unrestricted natural language text, which achieves a strict modularization of parsing algorithm, feature model and learning method such that these parameters can be varied independently. The architecture is based on the theoretical framework of inductive dependency parsing by Nivre \citeyear{nivre06c} and has been realized in MaltParser, a system that supports several parsing algorithms and learning methods, for which complex feature models can be defined in a special description language. LÄS MER