Ebook: Natural Language Processing: The PLNLP Approach

Natural language is easy for people and hard for machines. For two generations, the tantalizing goal has been to get computers to handle human languages in ways that will be compelling and useful to people. Obstacles are many and legendary.
Natural Language Processing: The PLNLP Approach describes one group's decade of research in pursuit of that goal. A very broad coverage NLP system, including a programming language (PLNLP) development tools, and analysis and synthesis components, was developed and incorporated into a variety of well-known practical applications, ranging from text critiquing (CRITIQUE) to machine translation (e.g. SHALT). This books represents the first published collection of papers describing the system and how it has been used. Twenty-six authors from nine countries contributed to this volume.
Natural language analysis, in the PLNLP approach, is done is six stages that move smoothly from syntax through semantics into discourse. The initial syntactic sketch is provided by an Augmented Phrase Structure Grammar (APSG) that uses exclusively binary rules and aims to produce some reasonable analysis for any input string. Its `approximate' analysis passes to the reassignment component, which takes the default syntactic attachments and adjusts them, using semantic information obtained by parsing definitions and example sentences from machine-readable dictionaries. This technique is an example of one facet of the PLNLP approach: the use of natural language itself as a knowledge representation language -- an innovation that permits a wide variety of online text materials to be exploited as sources of semantic information.
The next stage computes the intrasential argument structure and resolves all references, both NP- and VP-anaphora, that can be treated at this point in the processing. Subsequently, additional components, currently not so well developed as the earlier ones, handle the further disambiguation of word senses, the normalization of paraphrases, and the construction of a paragraph (discourse) model by joining sentential semantic graphs.
Natural Language Processing: The PLNLP Approach acquaints the reader with the theory and application of a working, real-world, domain-free NLP system, and attempts to bridge the gap between computational and theoretical models of linguistic structure. It provides a valuable resource for students, teachers, and researchers in the areas of computational linguistics, natural processing, artificial intelligence, and information science.

---

Natural language is easy for people and hard for machines. For two generations, the tantalizing goal has been to get computers to handle human languages in ways that will be compelling and useful to people. Obstacles are many and legendary.
Natural Language Processing: The PLNLP Approach describes one group's decade of research in pursuit of that goal. A very broad coverage NLP system, including a programming language (PLNLP) development tools, and analysis and synthesis components, was developed and incorporated into a variety of well-known practical applications, ranging from text critiquing (CRITIQUE) to machine translation (e.g. SHALT). This books represents the first published collection of papers describing the system and how it has been used. Twenty-six authors from nine countries contributed to this volume.
Natural language analysis, in the PLNLP approach, is done is six stages that move smoothly from syntax through semantics into discourse. The initial syntactic sketch is provided by an Augmented Phrase Structure Grammar (APSG) that uses exclusively binary rules and aims to produce some reasonable analysis for any input string. Its `approximate' analysis passes to the reassignment component, which takes the default syntactic attachments and adjusts them, using semantic information obtained by parsing definitions and example sentences from machine-readable dictionaries. This technique is an example of one facet of the PLNLP approach: the use of natural language itself as a knowledge representation language -- an innovation that permits a wide variety of online text materials to be exploited as sources of semantic information.
The next stage computes the intrasential argument structure and resolves all references, both NP- and VP-anaphora, that can be treated at this point in the processing. Subsequently, additional components, currently not so well developed as the earlier ones, handle the further disambiguation of word senses, the normalization of paraphrases, and the construction of a paragraph (discourse) model by joining sentential semantic graphs.
Natural Language Processing: The PLNLP Approach acquaints the reader with the theory and application of a working, real-world, domain-free NLP system, and attempts to bridge the gap between computational and theoretical models of linguistic structure. It provides a valuable resource for students, teachers, and researchers in the areas of computational linguistics, natural processing, artificial intelligence, and information science.

---

Natural language is easy for people and hard for machines. For two generations, the tantalizing goal has been to get computers to handle human languages in ways that will be compelling and useful to people. Obstacles are many and legendary.
Natural Language Processing: The PLNLP Approach describes one group's decade of research in pursuit of that goal. A very broad coverage NLP system, including a programming language (PLNLP) development tools, and analysis and synthesis components, was developed and incorporated into a variety of well-known practical applications, ranging from text critiquing (CRITIQUE) to machine translation (e.g. SHALT). This books represents the first published collection of papers describing the system and how it has been used. Twenty-six authors from nine countries contributed to this volume.
Natural language analysis, in the PLNLP approach, is done is six stages that move smoothly from syntax through semantics into discourse. The initial syntactic sketch is provided by an Augmented Phrase Structure Grammar (APSG) that uses exclusively binary rules and aims to produce some reasonable analysis for any input string. Its `approximate' analysis passes to the reassignment component, which takes the default syntactic attachments and adjusts them, using semantic information obtained by parsing definitions and example sentences from machine-readable dictionaries. This technique is an example of one facet of the PLNLP approach: the use of natural language itself as a knowledge representation language -- an innovation that permits a wide variety of online text materials to be exploited as sources of semantic information.
The next stage computes the intrasential argument structure and resolves all references, both NP- and VP-anaphora, that can be treated at this point in the processing. Subsequently, additional components, currently not so well developed as the earlier ones, handle the further disambiguation of word senses, the normalization of paraphrases, and the construction of a paragraph (discourse) model by joining sentential semantic graphs.
Natural Language Processing: The PLNLP Approach acquaints the reader with the theory and application of a working, real-world, domain-free NLP system, and attempts to bridge the gap between computational and theoretical models of linguistic structure. It provides a valuable resource for students, teachers, and researchers in the areas of computational linguistics, natural processing, artificial intelligence, and information science.

Content:
Front Matter....Pages i-xv
Introduction....Pages 1-11
Towards Transductive Linguistics....Pages 13-27
PEG: The PLNLP English Grammar....Pages 29-45
Experience with an Easily Computed Metric for Ranking Alternative Parses....Pages 47-52
Parse Fitting and Prose Fixing....Pages 53-64
Grammar Errors and Style Weaknesses in a Text-Critiquing System....Pages 65-76
The Experience of Developing a Large-Scale Natural Language Processing System: Critique....Pages 77-89
A Prototype English-Japanese Machine Translation System....Pages 91-99
Broad-Coverage Machine Translation....Pages 101-118
Building a Knowledge Base from Parsed Definitions....Pages 119-133
A Semantic Expert Using an Online Standard Dictionary....Pages 135-147
Structural Patterns versus String Patterns for Extracting Semantic Information from Dictionaries....Pages 149-159
SENS: The System for Evaluating Noun Sequences....Pages 161-173
Disambiguating and Interpreting Verb Definitions....Pages 175-189
Tailoring a Broad-Coverage System for the Analysis of Dictionary Definitions....Pages 191-202
PEGASUS: Deriving Argument Structures after Syntax....Pages 203-214
A Two-Stage Algorithm to Parse Multi-Lingual Argument Structures....Pages 215-226
C-SHALT: English-to-Chinese Machine Translation Using Argument Structures....Pages 227-245
Sense Disambiguation Using Online Dictionaries....Pages 247-261
Word-Sense Disambiguation by Examples....Pages 263-272
Normalization of Semantic Graphs....Pages 273-284
The Paragraph as a Semantic Unit....Pages 285-301
Back Matter....Pages 303-324

---

Natural language is easy for people and hard for machines. For two generations, the tantalizing goal has been to get computers to handle human languages in ways that will be compelling and useful to people. Obstacles are many and legendary.
Natural Language Processing: The PLNLP Approach describes one group's decade of research in pursuit of that goal. A very broad coverage NLP system, including a programming language (PLNLP) development tools, and analysis and synthesis components, was developed and incorporated into a variety of well-known practical applications, ranging from text critiquing (CRITIQUE) to machine translation (e.g. SHALT). This books represents the first published collection of papers describing the system and how it has been used. Twenty-six authors from nine countries contributed to this volume.
Natural language analysis, in the PLNLP approach, is done is six stages that move smoothly from syntax through semantics into discourse. The initial syntactic sketch is provided by an Augmented Phrase Structure Grammar (APSG) that uses exclusively binary rules and aims to produce some reasonable analysis for any input string. Its `approximate' analysis passes to the reassignment component, which takes the default syntactic attachments and adjusts them, using semantic information obtained by parsing definitions and example sentences from machine-readable dictionaries. This technique is an example of one facet of the PLNLP approach: the use of natural language itself as a knowledge representation language -- an innovation that permits a wide variety of online text materials to be exploited as sources of semantic information.
The next stage computes the intrasential argument structure and resolves all references, both NP- and VP-anaphora, that can be treated at this point in the processing. Subsequently, additional components, currently not so well developed as the earlier ones, handle the further disambiguation of word senses, the normalization of paraphrases, and the construction of a paragraph (discourse) model by joining sentential semantic graphs.
Natural Language Processing: The PLNLP Approach acquaints the reader with the theory and application of a working, real-world, domain-free NLP system, and attempts to bridge the gap between computational and theoretical models of linguistic structure. It provides a valuable resource for students, teachers, and researchers in the areas of computational linguistics, natural processing, artificial intelligence, and information science.

Content:
Front Matter....Pages i-xv
Introduction....Pages 1-11
Towards Transductive Linguistics....Pages 13-27
PEG: The PLNLP English Grammar....Pages 29-45
Experience with an Easily Computed Metric for Ranking Alternative Parses....Pages 47-52
Parse Fitting and Prose Fixing....Pages 53-64
Grammar Errors and Style Weaknesses in a Text-Critiquing System....Pages 65-76
The Experience of Developing a Large-Scale Natural Language Processing System: Critique....Pages 77-89
A Prototype English-Japanese Machine Translation System....Pages 91-99
Broad-Coverage Machine Translation....Pages 101-118
Building a Knowledge Base from Parsed Definitions....Pages 119-133
A Semantic Expert Using an Online Standard Dictionary....Pages 135-147
Structural Patterns versus String Patterns for Extracting Semantic Information from Dictionaries....Pages 149-159
SENS: The System for Evaluating Noun Sequences....Pages 161-173
Disambiguating and Interpreting Verb Definitions....Pages 175-189
Tailoring a Broad-Coverage System for the Analysis of Dictionary Definitions....Pages 191-202
PEGASUS: Deriving Argument Structures after Syntax....Pages 203-214
A Two-Stage Algorithm to Parse Multi-Lingual Argument Structures....Pages 215-226
C-SHALT: English-to-Chinese Machine Translation Using Argument Structures....Pages 227-245
Sense Disambiguation Using Online Dictionaries....Pages 247-261
Word-Sense Disambiguation by Examples....Pages 263-272
Normalization of Semantic Graphs....Pages 273-284
The Paragraph as a Semantic Unit....Pages 285-301
Back Matter....Pages 303-324
....