Natural Language Processing in Prolog (Gerald GazdarChris Mellish)
January 4th, 2008 | posted by adminChapter 1 looks briefly at the origins of natural language processing, the emergence of structural notions in NLP, the ways in which researchers have attempted to represent meaning, the increasing appreciation of the role of real-world knowledge, and the early indications that NLP is moving from academic research into commercial technology. The chapter concludes by considering the appropriateness of using Prolog for NLP.
Chapter 2 is devoted to finite state techniques for NLP, beginning with finite state transition networks and their implementation in Prolog, moving on to the more interesting and useful finite state transducers, and concluding with a brief look at the limitations of finite state machines.
Chapter 3 moves to the recursive and augmented transition networks, showing how the former can be used to model recursive phenomena in English, how they can be implemented in Prolog, and what their limitations are. After considering the pushdown transducers, augmented transition networks are introduced, their implementation considered, and their inherently procedural character noted.
Chapter 4 considers the declarative representation of grammars, words, rules and structures, and introduces the PATR grammar formalism that is used throughout the rest of the book. Subcategorization, the use of features, encoding feature specifications in Prolog,
context-free, finite-state, and indexed grammars and languages, are among the topics discussed in some detail.
Chapter 5 looks at parsing, search and ambiguity, cosiders a simple parsing problem is minute detail, distinguishes bottom-up from top-down parsing, and breadth first from depth first search strategies, touches on the possibility of storing intermediate results, investigates the major sources of ambiguity, and explains determinism and lookahead.
Chapter 6 pursues the possibility of storing intermediate results in great detail by introducing well-formed substring tables & charts. The fundamental rule of active chart parsing is discussed, as are such topics as chart initialization, rule invocation, search strategy, housekeeping, efficiency, and alternative rule invocation strategies.
Chapter 7, the longest chapter in the book, develops the feature-theoretic view of syntax and then goes on to look at the nature of the lexicon presupposed by feature-based language models. Feature structures are treated as graphs and implemented in Prolog, subsumption and unification are defined, and a Prolog realization of PATR is presented. Issues that arise in chart parsing with feature-based grammars, such as copying, duplication checking, indexing, and the conflation of similar edges, are discussed. The rest of the chapter is devoted to the representation of lexical knowledge and the implemention of a lexicon in Prolog.
Chapter 8 moves from syntax to semantics via the notion of compositionality, and a look at meaning as reference. The issues that arise in translating English to a meaning representation language then take over, and a database query language DBQ is presented. Thinking of computational semantics as feature instantiation leads to consideration of transitive verbs and quantification, ambiguity, preferences and timing, and the possibility of building semantic checking into the grammar.
Chapter 9 goes on to question answering and inference, including such topics as the evaluation of DBQ formulae, standard logical inference, the implementation in Prolog of backwards and forwards inference, the pathological nature of logical inference, primitives and canonical forms, inheritance and defaults. It concludes by presenting a simple semantic network in Prolog.
Chapter 10 shifts from semantics to pragmatics, initially by considering the semantic and pragmatic roles of noun phrases. The chapter goes on to present the contrast given and new information, the notion of understanding by prediction, and the use of discourse structure. It ends by presenting language generation as a goal-oriented process and language understanding as plan recognition.
To Download this E-Book Click Here.













Recent comments
10 weeks 4 days ago
19 weeks 3 days ago
24 weeks 1 day ago
25 weeks 1 day ago
25 weeks 2 days ago
25 weeks 2 days ago
36 weeks 1 day ago
36 weeks 2 days ago
36 weeks 4 days ago
37 weeks 1 day ago