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 foundation...
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.
目录
· · · · · ·
Introduction
Mathematical Foundations
Linguistic Essentials
Corpus-Based Work
Collocations
Statistical Inference: n-gram Models over Sparse Data
· · · · · ·
(更多)
Introduction
Mathematical Foundations
Linguistic Essentials
Corpus-Based Work
Collocations
Statistical Inference: n-gram Models over Sparse Data
Word Sense Disambiguation
Lexical Acquisition
Markov Models
Part-of-Speech Tagging
Probabilistic Context Free Grammars
Probabilistic Parsing
Statistical Alignment and Machine Translation
Clustering
Topics in Information Retrieval
Text Categorization
· · · · · · (收起)
We suspect that speech recognition people prefer to report the larger
non-logarithmic numbers given by perplexity mainly because it is much
easier to
impress funding bodies
by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced
cross entropy from 9.9 to 9.1 bits.” (查看原文)
This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, ...This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, even Philosophy and Neurosciences if you want to know more about NLP(展开)
This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, ...This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, even Philosophy and Neurosciences if you want to know more about NLP(展开)
We suspect that speech recognition people prefer to report the larger non-logarithmic numbers given by perplexity mainly because it is much easier to impress funding bodies by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced cross entropy from 9.9 to 9.1 bits.” 论科研的辛酸。。。
2016-03-07 02:24:23
We suspect that speech recognition people prefer to report the larger
non-logarithmic numbers given by perplexity mainly because it is much
easier to
impress funding bodies
by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced
cross entropy from 9.9 to 9.1 bits.”引自第78页
We suspect that speech recognition people prefer to report the larger non-logarithmic numbers given by perplexity mainly because it is much easier to impress funding bodies by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced cross entropy from 9.9 to 9.1 bits.” 论科研的辛酸。。。
2016-03-07 02:24:23
We suspect that speech recognition people prefer to report the larger
non-logarithmic numbers given by perplexity mainly because it is much
easier to
impress funding bodies
by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced
cross entropy from 9.9 to 9.1 bits.”引自第78页
We suspect that speech recognition people prefer to report the larger non-logarithmic numbers given by perplexity mainly because it is much easier to impress funding bodies by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced cross entropy from 9.9 to 9.1 bits.” 论科研的辛酸。。。
2016-03-07 02:24:23
We suspect that speech recognition people prefer to report the larger
non-logarithmic numbers given by perplexity mainly because it is much
easier to
impress funding bodies
by saying that “we’ve managed to reduce perplexity from 950 to only 540” than by saying that “we’ve reduced
cross entropy from 9.9 to 9.1 bits.”引自第78页
0 有用 马文 2018-08-28 02:15:15
This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, ... This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, even Philosophy and Neurosciences if you want to know more about NLP (展开)
0 有用 最上川 2020-02-28 12:39:43
看完了(心虚
0 有用 王亮 2015-11-22 15:28:39
书写的挺好,就是比较过时了。。。
1 有用 Luke 2017-11-28 14:58:21
经典
0 有用 锂子果 2014-03-04 00:17:26
entropy
0 有用 最上川 2020-02-28 12:39:43
看完了(心虚
0 有用 马文 2018-08-28 02:15:15
This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, ... This book published 20 years ago, but the content still new to me. Statistical NLP is the most interdisciplinary in my view, it involves Linguistics, Computer Science, Statistics, Information Theory, even Philosophy and Neurosciences if you want to know more about NLP (展开)
1 有用 Luke 2017-11-28 14:58:21
经典
0 有用 王亮 2015-11-22 15:28:39
书写的挺好,就是比较过时了。。。
0 有用 Sweetdumplings 2015-11-01 09:08:49
作为NLP领域最主要的理论入门书,这本书深入浅出地展示了很多经典的模型算法,虽然现在看有点偏老了,也没有涉及最近很火的deep learning,但是作为入门绝对是足够的。