## Foundations of Statistical Natural Language ProcessingStatistical approaches to processing natural language text have become dominant in recent years. This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear. The book contains all the theory and algorithms needed for building NLP tools. It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations. The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, and other applications. |

### Contents

3 | |

60 | 24 |

Mathematical Foundations | 39 |

Linguistic Essentials | 81 |

78 | 114 |

CorpusBased Work | 117 |

Collocations | 151 |

ngram Models over Sparse Data | 191 |

PartofSpeech Tagging | 341 |

Probabilistic Context Free Grammars | 381 |

Probabilistic Parsing | 407 |

Statistical Alignment and Machine Translation | 463 |

Clustering | 495 |

Topics in Information Retrieval | 529 |

Text Categorization | 575 |

Text Categorization | 607 |

### Other editions - View all

Foundations of Statistical Natural Language Processing Christopher Manning,Hinrich Schutze Limited preview - 1999 |

Foundations of Statistical Natural Language Processing Christopher Manning,Hinrich Schutze Limited preview - 1999 |

Foundations of Statistical Natural Language Processing Christopher Manning,Hinrich Schutze No preview available - 1999 |

### Common terms and phrases

actually algorithm alignment ambiguous applied approach assume attachment basic better bigrams Brown calculate chapter clustering collocations complex compute context corpus corresponding counts decision defined depends derivation described determine dictionary disambiguation discussed distribution documents English entropy estimate example Exercise expected expression figure frame frequency function give given grammar head important indicates interest language learning lexical likelihood linguistics look Markov maximum meaning measure methods n-gram node normally Note noun object occur parameters parsing particular performance phrase possible preposition present probabilistic probability problem question refer rule selectional semantic sense sentence sequence shown shows similarity simply space speech Statistical Statistical NLP structure syntactic theory things tion translation tree usually values variable vector verb weight words