Book Reviews: Foundations of Statistical Natural Language Processing

By Christopher D. Manning, Hinrich Schütze. 1999

Statistical 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.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Differentially Private Learning Needs Better Features (or Much More Data) (2020, background): “Another interesting direction is to extend our results to domains beyond vision, e.g., with handcrafted features for text (Manning & Schutze, 1999) or speech (Andén & Mallat, 2014).”
Wireless Network Intelligence at the Edge (2018, background): “Mathematically, playing this game is identical to minimizing the Jensen-Shannon (JS) divergence [79] between the real and generated sample distributions.”
A Survey on Neural Speech Synthesis (2021, background): “Text to speech (TTS), also known as speech synthesis, which aims to synthesize intelligible and natural speech from text [340], has broad applications in human communication [1] and has long been a research topic in artificial intelligence, natural language and speech processing [290, 222, 144].”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, methodology): “video and text in the form of a parse graph. A parse graph is a labeled directed graph that can be seen as an extension of the constituency-based parse tree used in natural language syntactic parsing [5]. It has been employed in computer vision to model objects [6], scenes [7], [8] and events [9], [”
Gmail Smart Compose: Real-Time Assisted Writing (2019, background): “Language modelling is a fundamental and indispensable component of many natural language processing (NLP) and automatic speech recognition (ASR) systems [23, 27, 32, 35].”
Visual Question Generation as Dual Task of Visual Question Answering (2017, background): “Question answering (QA) and question generation (QG) are two fundamental tasks in natural language processing [24, 25].”
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (2019, methodology): “We report the diversity metrics used for evaluating E2E challenge submissions in Dušek et al. (2019) (# unique tokens, # unique trigrams, Shannon token entropy (Manning and Schütze, 1999, p.61ff.), conditional bigram entropy (Manning and Schütze, 1999, p.63ff.)).”
An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification (2017, background): “From a natural language point of view, cognates are “words that are similar across languages” (Manning and Sch¨utze, 1999).”
Ask Your Neurons: A Deep Learning Approach to Visual Question Answering (2016, background): “In this work we investigate a Bag-Of-Words (BOW), a CNN, and two RNN variants (LSTM (Hochreiter and Schmidhuber, 1997) and GRU (Cho et al, 2014)) to encode the question.”
High-dimensional Ising model selection using ℓ1-regularized logistic regression (2010, background): “Markov random ﬁelds. 1. Introduction. Undirected graphical models, also known as Markov random ﬁelds, are used in a variety of domains, including statistical physics [17], natural language processing [21], image analysis [8, 14, 37] and spatial Received October 2008; revised January 2009. 1Supported”
Parsing Videos of Actions with Segmental Grammars (2014, methodology): “, wN , the CYK algorithm is a O(nRN (3)) dynamic programming algorithm for computing the best-scoring parse [14].”
The Deep Learning Compiler: A Comprehensive Survey (2020, background): “nt of deep learning (DL) has generated profound impact on various scientific fields. It has not only demonstrated remarkable value in artificial intelligence such as natural language processing (NLP) [68] and computer vision (CV) [39], but also proved great success in broader applications such as e-”
Image Parsing: Unifying Segmentation, Detection, and Recognition (2003, unknown): “The parsing graph is similar in spirit to the parsing trees used in speech and natural language processing [ 33 ] except that it can include horizontal connections (see the dashed curves in Figure 1) for specifying spatial relationships and boundary sharing between different visual patterns.”