دانلود کتاب Linguistic Resources for Natural Language Processing: On the Necessity of Using Linguistic Methods to Develop NLP Software

فهرست مطالب :

Foreword
Preface
About This Book
Contents
Part I: Introduction
The Limitations of Corpus-Based Methods in NLP
1 Introduction
1.1 Training Corpora
1.2 Limited Tag Sets
1.3 Reliability of Training Corpora
2 NLP Software Results
2.1 Incorrect Tags
2.2 Concepts, Themes, and Terms
2.3 Word Clouds
2.4 Semantic Networks
3 Principles at the Basis of Empirical Methods
3.1 Flawed Principle: The Notion of Similar Contexts
3.2 Flawed Principle: The Units of Processing
4 The Scientific Approach
4.1 The Real Value of a Training Corpus
5 Conclusion
References
Part II: Developing Linguistic-Based NLP Software
Linguistic Resources for the Automatic Generation of Texts in Natural Language: The Elvex Formalism
1 Introduction
2 A Hypothetico-deductive Approach of NLG
2.1 A Deterministic Model
2.2 A Declarative and Constraint-Based Approach
2.3 A Monotonic Model
3 Writing a Grammar with Elvex
3.1 Feature Structure
3.2 Constituent-Structure (C-Structure)
3.3 Syntactic Rules
3.4 The Lexicon
The Morphological Lexicon Defined by Extension
The Pattern Lexicon
3.5 The Language Rules
3.6 The Speaker´s Rules and Language
4 Conclusion
References
Towards a More Efficient Arabic-French Translation
1 Introduction
2 Related Works
3 Problems in Arabic Named Entities
3.1 Problems in Recognition
3.2 Problems with the Translation of Arabic NEs
4 Implementation of the Set of Transducers
4.1 Recognition Phase
4.2 Translation Phase
5 Experimentation and Evaluation
5.1 Experimentation of Recognition Phase
5.2 Experimentation of Translation Phase
6 From the NEs Recognition to the Translation of Complex Sentences
6.1 NEs and Relative Clauses
6.2 Implemented Resources
6.3 Experimentation of Implemented Resources
7 Conclusion and Perspectives
References
Linguistic Resources and Methods for Belarusian Natural Language Processing
1 Introduction
2 Text-to-Speech Synthesizer
3 The Transcription Generator
4 Word Paradigm Generator
5 Conclusion
References
Part III: Linguistic Resources for Low-Resource Languages
A New Set of Linguistic Resources for Ukrainian
1 Introduction
2 Theoretical Basis
2.1 Approaches to Designing Natural Language Processing Applications
3 Statistical Tools for Ukrainian
3.1 Sketch ENGINE
3.2 TreeTagger and RNNTagger
4 Ukrainian Linguistic Resources
4.1 Dictionary
4.2 Morphological Grammars
5 Conclusion and Perspectives
References
Formalization of the Quechua Morphology
1 Introduction
2 Constructing Electronic Dictionaries
2.1 Formalization of Quechua Noun Inflections
2.2 Formalizing Quechua Verb Morphology
2.3 Formalizing Adjective Morphology
2.4 Formalizing Adverbs Morphology
2.5 Formalizing Pronouns Morphology
3 Conclusion and Perspectives
References
The Challenging Task of Translating the Language of Tango
1 Introduction
2 The Project: Automatic Machine Translation
3 Translation of Terms
4 Translating Syntactic Structures
5 Conclusion
References
A Polylectal Linguistic Resource for Rromani
1 Introduction
1.1 Rromani Dialectology
1.2 Rromani Alphabet
1.3 Rromani Dictionaries
1.4 Rromani Language Lessons
1.5 Rromani Grammar
2 Empirical NLP Software
2.1 Rromani, a Low-Resource Language
3 Rromani Online Resources
3.1 Russian Romani Corpus
3.2 ROMLEX
3.3 Online Rromani Dictionaries
3.4 Need for Coherent Linguistic Resources
4 Rromani Linguistic Resources
4.1 Dictionary
4.2 Morphology
5 Evaluation and Perspectives
References
Part IV: Processing Multiword Units: The Linguistic Approach
Using Linguistic Criteria to Define Multiword Units
1 Introduction
2 The Corpus-Based Approach and Collocations
3 Semantic Atomicity
4 Term Usage
5 Idiosyncratic Transformational Analyses
6 Conclusion
References
A Linguistic Approach to English Phrasal Verbs
1 Introduction
2 English Phrasal Verbs: Particle vs. Preposition
2.1 Further Distinctions: Prepositional and Phrasal Prepositional Verbs
3 Lexicon-Grammar of Phrasal Verbs
3.1 Using Lexicon-Grammar in Tandem with NooJ
3.2 Accuracy of Discontinuous Phrasal Verbs
4 Removing False Phrasal Verbs Automatically
4.1 PV Disambiguation Grammar 1: Environment to Right of ``PV´´
4.2 PV Disambiguation Grammar 2: Environment to Left of ``PV´´
4.3 PV Disambiguation Grammar 3: Locative Environment to Right of ``PV´´
5 Conclusion
References
Analysis of Indonesian Multiword Expressions: Linguistic vs Data-Driven Approach
1 Introduction
2 POS Tagging
3 Syntactic Parsing
4 Machine Translation
5 Conclusion
References