What do you think?
Rate this book
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
For undergraduate or advanced undergraduate courses in Classical Natural Language Processing, Statistical Natural Language Processing, Speech Recognition, Computational Linguistics, and Human Language Processing. An explosion of Web-based language techniques, merging of distinct fields, availability of phone-based dialogue systems, and much more make this an exciting time in speech and language processing. An accompanying Website contains teaching materials for instructors, with pointers to language processing resources on the Web. The Second Edition offers a significant amount of new and extended material.
1024 pages, Paperback
First published January 26, 2000
162 people are currently reading
1988 people want to read
About the author
Dan Jurafsky
6 books84 followersDan Jurafsky is the recipient of a MacArthur "Genius Grant" and a professor of linguistics at Stanford University. He and his wife live in San Francisco.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 30 of 51 reviews
June 2, 2013
I found this book comprehensive but incomprehensible, primarily because of the lack of real-world examples. It would benefit from a series of programming exercises with training sets made available through a web site. This would tie the extremely abstract algorithms to technology and data. If you are a strong computer scientist with lots of experience in abstract algorithms, this book should give you what you need. If you are interested in producing real-world software systems to do serious speech and language work, start here but be prepared to go elsewhere for practical tools, methods, and advice about implementation. It's instructive to look at Jurafsky and Martin's Coursera online course based on this book--much more practical and hands on. The book doesn't help much when you take that course.
May 18, 2017
A fundamental and useful book. Would highly recommend for anyone interested in Natural Language Processing.
Read
September 9, 2020یک کتاب اساسی و مفید. برای کسانی که به پردازش زبان طبیعی علاقه مند هستند بسیار توصیه می شود.
March 17, 2023
Very much aimed at CS or engineering undergrads coming to the field with their baggage but zero experience in linguistics, not linguists looking to expand into computer bullshit. This manifests itself not just in its assumption that you're already basically familiar with a lot of CS-specific jargon, but also in its sloppiness with linguistic jargon and the making of certain choices that no linguist ever would (such as the use of ARPAbet, a phonetic transcription system you won't have heard of because it is absolute garbage and specific to American English). Much of the theory depends on straightforward but occasionally non-trivial statistics, and here you get that peculiar brand of notation abuse that seems to be specific to computer scientists writing at the edge of their own ability, and the treatment ends up ping-ponging between condescendingly trivial and unparseable symbol salad quite a lot—this is where using this textbook in the context of a class rather than on your own pays off, not because the concepts are hard but because they're poorly communicated.
Conspicuously American, the authors also get much of their conception of how linguistics works from Chomsky and his acolytes, without seeming to be aware of the problems with more or less his entire body of work when applied to actual natural languages; the chapters on Computational Phonology and Computational Semantics in particular are shockingly weak and based on premises that just... don't work, and while an attempt is made to have the described algorithms be generally applicable, much more of the book is entirely specific to English and not really (or only barely) generalisable than Jurafsky and Martin seem to realise.
The early chapters are nice if you're writing, like, a parser or a spellchecker or a very simple chatbot, but I don't know that I'd consider any of that to be speech or language processing. The later chapters clearly are, but their practical applicability is often questionable, and that's usually more due to how they're written than to their actual contents.
A class that uses this as a textbook could be good, depending on which chapters it focuses on. As an introduction to read cover to cover and to keep on hand as a reference, it's just kind of frustrating.
Conspicuously American, the authors also get much of their conception of how linguistics works from Chomsky and his acolytes, without seeming to be aware of the problems with more or less his entire body of work when applied to actual natural languages; the chapters on Computational Phonology and Computational Semantics in particular are shockingly weak and based on premises that just... don't work, and while an attempt is made to have the described algorithms be generally applicable, much more of the book is entirely specific to English and not really (or only barely) generalisable than Jurafsky and Martin seem to realise.
The early chapters are nice if you're writing, like, a parser or a spellchecker or a very simple chatbot, but I don't know that I'd consider any of that to be speech or language processing. The later chapters clearly are, but their practical applicability is often questionable, and that's usually more due to how they're written than to their actual contents.
A class that uses this as a textbook could be good, depending on which chapters it focuses on. As an introduction to read cover to cover and to keep on hand as a reference, it's just kind of frustrating.
May 14, 2015
Jurafsky provides a solid foundational knowledge for computational linguistic - it introduces linguistics, computer science and statistics at comprehensive depth.
Some of the major concepts for anybody who wants to know about computational linguistic.
Language Model: the book introduces basic models and algorithms evolved around linguistics. There are two major approaches: 1) statistics-based parsing 2) linguistic-based parsing. In practice, most models are built with mixture of both.
Part-of-Speech tagging: a task of labelling words into certain category. This challenge relies on language models - N-Grams, and Hidden Markov Model.
Hidden Markov Model (HMM): it's the foundation for many computational linguistic task. The core concept is that language has an extrinsic state (the words we see) and an intrinsic state (syntax and semantic structure behind the sentence), and by keeping track of intrinsic state we can have a better understanding of extrinsic states. Specifically, there are major Dynamic Algorithms such as Forward Algorithm and Viterbi Algorithm that use HMM to classify and predict language models.
Context-Free Grammar: put it simply, it's the syntax tree for human language as Abstract Syntax Tree (AST) for computer language, although there are more nuisances as human language is less structured. Given a sentence, there are "top-down" and "bottom-up" algorithms that generate a parse tree.
Probabilistic Context-Free Grammar: most times sentences have multiple parse tree candidate, if we have a pre-trained corpus, we can then assign probability to each candidate tree, the book also talks about algorithms to do that.
Discourse analysis: two major tasks have been introduced - anaphora resolution (ie. what does "it" refer to?) and speech coherence. Idioms have been established around how to resolve anaphora by using salience value (recency, subject, object), and how to analyze coherence (Rhetoric Structure Theory)
Dialogue System: this is the chapter that interest me the most. The author talks about the turn-taking nature of dialogue and maxims to follow when developing a dialogue system. Many technical specifications can be implemented using tricks covered in previous chapters.
Machine Translation: most machine translation models are statistical. Two major factors to integrate: word occurrence (How like is source word S to be translated to target word T?) and alignment (how likely is source word S to be in the same order as target word T?). On top, we use Bayes rules to calculate probabilities.
All in all, it's a comprehensive book, I really enjoyed it. There are some new chapters coming out of the new edition which I like better.
Some of the major concepts for anybody who wants to know about computational linguistic.
Language Model: the book introduces basic models and algorithms evolved around linguistics. There are two major approaches: 1) statistics-based parsing 2) linguistic-based parsing. In practice, most models are built with mixture of both.
Part-of-Speech tagging: a task of labelling words into certain category. This challenge relies on language models - N-Grams, and Hidden Markov Model.
Hidden Markov Model (HMM): it's the foundation for many computational linguistic task. The core concept is that language has an extrinsic state (the words we see) and an intrinsic state (syntax and semantic structure behind the sentence), and by keeping track of intrinsic state we can have a better understanding of extrinsic states. Specifically, there are major Dynamic Algorithms such as Forward Algorithm and Viterbi Algorithm that use HMM to classify and predict language models.
Context-Free Grammar: put it simply, it's the syntax tree for human language as Abstract Syntax Tree (AST) for computer language, although there are more nuisances as human language is less structured. Given a sentence, there are "top-down" and "bottom-up" algorithms that generate a parse tree.
Probabilistic Context-Free Grammar: most times sentences have multiple parse tree candidate, if we have a pre-trained corpus, we can then assign probability to each candidate tree, the book also talks about algorithms to do that.
Discourse analysis: two major tasks have been introduced - anaphora resolution (ie. what does "it" refer to?) and speech coherence. Idioms have been established around how to resolve anaphora by using salience value (recency, subject, object), and how to analyze coherence (Rhetoric Structure Theory)
Dialogue System: this is the chapter that interest me the most. The author talks about the turn-taking nature of dialogue and maxims to follow when developing a dialogue system. Many technical specifications can be implemented using tricks covered in previous chapters.
Machine Translation: most machine translation models are statistical. Two major factors to integrate: word occurrence (How like is source word S to be translated to target word T?) and alignment (how likely is source word S to be in the same order as target word T?). On top, we use Bayes rules to calculate probabilities.
All in all, it's a comprehensive book, I really enjoyed it. There are some new chapters coming out of the new edition which I like better.
February 26, 2019
I haven't read this book cover to cover but it's always on my desk and I find myself referring to it at least once a day, and in that, I believe I probably read most of its contents. This is a fundamental reference book for any computational linguist, speech scientist or language data scientist. The explanations and illustrations are very intuitive and not at all boring.
January 7, 2021
+Great book introducing Speech and Language Processing concepts as well as some basic (and more advanced) machine learning applications.
+Covers a wide range of applications and methods related to speech and language processing.
-Goes into depth on some concepts which might not be common in practice.
+Covers a wide range of applications and methods related to speech and language processing.
-Goes into depth on some concepts which might not be common in practice.
August 20, 2025
Absolutely awesome book about the fundamentals and applications of NLP.
January 30, 2024
Update:
The book was once again literature for a class of mine (this time also further, until chapter 17?) and after spending quite some time in the field of NLP I can say that it is one of the best resources I've ever found regarding algorithms, explanations and examples.
_________________________________________
I just read until chapter 9, as it was the literature for my class, and I have to say that this book is a really good source for NLP. And I will definitely continue it and use it as a source in the future.
The topics, as complex as they might be, are well explained, often represented within graphics and followed by many examples. There are even some pseudo codes that can be used as a guidance.
A variety of models that are important were shown and compared as of what their advantages and disadvantages are and for what kind of tasks they might be used for. All in all a really good overview.
There are also playlists on YouTube where the most important processes are being explained and shown, which is an efficient addition, if the text alone might be too heavy to read.
Only critic I have so far: some parts are too repetitive. One information is sometimes displayed up to three or four times within the same chapter. As important as it might be, I sometimes got frustrated to reread the same thing again and again. Maybe it just annoyed me because I read chapter to chapter and did not use it as an resourcebook, but well.
The book was once again literature for a class of mine (this time also further, until chapter 17?) and after spending quite some time in the field of NLP I can say that it is one of the best resources I've ever found regarding algorithms, explanations and examples.
_________________________________________
I just read until chapter 9, as it was the literature for my class, and I have to say that this book is a really good source for NLP. And I will definitely continue it and use it as a source in the future.
The topics, as complex as they might be, are well explained, often represented within graphics and followed by many examples. There are even some pseudo codes that can be used as a guidance.
A variety of models that are important were shown and compared as of what their advantages and disadvantages are and for what kind of tasks they might be used for. All in all a really good overview.
There are also playlists on YouTube where the most important processes are being explained and shown, which is an efficient addition, if the text alone might be too heavy to read.
Only critic I have so far: some parts are too repetitive. One information is sometimes displayed up to three or four times within the same chapter. As important as it might be, I sometimes got frustrated to reread the same thing again and again. Maybe it just annoyed me because I read chapter to chapter and did not use it as an resourcebook, but well.
May 31, 2017
This book's reputation as a classic NLP text is well deserved. Numerous diagrams, illustrations, and explanations helped me to understand this bewildering subject. Because this is an academic text book, there are many equations, but few practical examples. For down-and-dirty examples, you might be better served with internet tutorials or the O'Reilly book. But if you want to understand why things work they way they do, this book is great.
October 3, 2012
Very interesting & useful book for everybody who is interested in natural language processing. I read it when I took online NLP class from prof. Jurafsky at Coursera, and found many interesting things there.
I really didn't read it completely, for example, I omitted the speech recognition part, but I plan to return to this book in the near future...
I really didn't read it completely, for example, I omitted the speech recognition part, but I plan to return to this book in the near future...
May 24, 2021
My favourite reference for Natural Language Processing algorithms and applications. Daniel Jurafski has a brilliant way of explaining things! Highly recommend it for anyone looking to make a career in NLP.
May 29, 2023
A classic and comprehensive text in Natural Language Processing, updated to bring the reader up to the transformers era. It continues to offer extensive coverage of classic methods and ideas in NLP and linguistics, but is reorganized and edited to explain how the classic ideas contribute to the development and understanding of neural network methods that now completely dominate the field. As a draft, some of the content on these newer ideas is still in progress, but even as is it offers a solid foundation.
The first 2 sections of the book, on ideas and applications, respectively, follow this agenda and work well together. The third section, on linguistic structure, feels like a bit of a grab bag of old NLP ideas which used to be central to breaking down language inside the rule-based systems that were used in earlier eras. Now, many of the primary tasks which were thought to need these components (like syntax parsing or coreference resolution) are often outperformed by fully end-to-end systems which do not rely on dedicated subsystems for these tasks, so they are now mainly of interest for linguistic understanding. And for each of them, chapter after chapter goes through a path of explaining a basic idea, complicated rule based systems designed to implement it, and then a few paragraphs at the end explaining the neural systems that strongly outperform the rules at that task for even if you did want to accomplish it. As a person interested in applications, I found this last part less useful, but it did serve to reinforce the sense (mainly secondhand from hanging out with NLP researchers at dinner parties) of how completely the field has changed since the previous edition of the book.
The first 2 sections of the book, on ideas and applications, respectively, follow this agenda and work well together. The third section, on linguistic structure, feels like a bit of a grab bag of old NLP ideas which used to be central to breaking down language inside the rule-based systems that were used in earlier eras. Now, many of the primary tasks which were thought to need these components (like syntax parsing or coreference resolution) are often outperformed by fully end-to-end systems which do not rely on dedicated subsystems for these tasks, so they are now mainly of interest for linguistic understanding. And for each of them, chapter after chapter goes through a path of explaining a basic idea, complicated rule based systems designed to implement it, and then a few paragraphs at the end explaining the neural systems that strongly outperform the rules at that task for even if you did want to accomplish it. As a person interested in applications, I found this last part less useful, but it did serve to reinforce the sense (mainly secondhand from hanging out with NLP researchers at dinner parties) of how completely the field has changed since the previous edition of the book.
July 29, 2023
“It’s that damn NLP. He’s so hot right now.” — Mugatu
Phew… This one took me just over 1-year to get through. Definitely a Marathon. Definitely worth it.
But for real, NLP is such an exciting space: Linguistics + Math + Computer Science. Made all the more exciting because, unlike other fields of arcane engineering, every single one of us is hyper familiar with language! We intuitively know all the rules and use them every day.
If I’m being honest, a lot of math and more advanced AI went over my head; it would be helpful to have familiarity with AI algos first, but you can still get a general idea of the theories without that. Dig deeper if you ever want to actually build stuff.
Now, this book was published right before GPT-3. That places it at an interesting time. It is aware of Large Language Models, and it definitely covers LLMs, Transformers, BERT, etc., but it doesn’t cover their recent explosion.
It’s quite amazing to see how many of the problems arduously analyzed in this book might just be solved by this new class of LLMs. In fact, it’s a bit comedic to read how much work has gone into deeply defining and laying out the relationships between words, sentences, ideas, complex linguistic structures, etc… And then you create a ChatGPT—basically just a collection of neural weights that predict one word at a time—and it probably just outperforms everything.
Phew… This one took me just over 1-year to get through. Definitely a Marathon. Definitely worth it.
But for real, NLP is such an exciting space: Linguistics + Math + Computer Science. Made all the more exciting because, unlike other fields of arcane engineering, every single one of us is hyper familiar with language! We intuitively know all the rules and use them every day.
If I’m being honest, a lot of math and more advanced AI went over my head; it would be helpful to have familiarity with AI algos first, but you can still get a general idea of the theories without that. Dig deeper if you ever want to actually build stuff.
Now, this book was published right before GPT-3. That places it at an interesting time. It is aware of Large Language Models, and it definitely covers LLMs, Transformers, BERT, etc., but it doesn’t cover their recent explosion.
It’s quite amazing to see how many of the problems arduously analyzed in this book might just be solved by this new class of LLMs. In fact, it’s a bit comedic to read how much work has gone into deeply defining and laying out the relationships between words, sentences, ideas, complex linguistic structures, etc… And then you create a ChatGPT—basically just a collection of neural weights that predict one word at a time—and it probably just outperforms everything.
February 1, 2025
Hands-down that this is the top textbook of natural language processing out there. It's a big book, but it will walk you from knowing nothing to fully comprehending how something like ChatGPT works.
Full-disclaimer: I'm not from a computer science background, and I wrote my first Python line of code literally a few weeks before I picked up this book. I have been through three Ivy League school classes that had it as an assigned reading, among others, and it was always the most superior reading. It starts from scratch, assumes no previous knowledge of machine learning, tech, or linguistics, and explains everything about these fields at a near perfect pace.
In my mind, the target audience of this book is complete NLP dummies - with the critical nuance that it is for dummies (like me) who wish to become experts. It's not a generic introduction, it doesn't give you a generalist's overview. It's a fairly technical textbook with all the algorithms and the sausage making of natural language AI, starting from its naive beginnings and up to state-of-the-art large language models. It does, however, guide you through this long journey gently, step-by-step, if you're willing to put-in the effort to follow along.
For a CompSci major, my guess is that this is an average introductory read. For the rest of us, it could be a fairly challenging and technical book. If you are seriously interested in the field, though, you will hardly find a better starting point. Forget about youtube video on transformers, they will just get you more confused. LLMs are an impressive invention that is contingent on a long chain of innovations, so you can never truly understand them without taking the full story / narrative in a long book format.
If this book made me appreciate anything, it's the amount of ingenuity that went into what became ChatGPT. It wasn't a single brilliant idea, but 70 years of brilliantly clever ideas that accumulated one after the other to deliver this mindblowing piece of technology. One thing remains very mind boggling to me after reading it: in spite of all the genius that went into compiling LLMs, everything I learned still hardly makes me belive that it is enough to make ChatGPT do the things it does.
Full-disclaimer: I'm not from a computer science background, and I wrote my first Python line of code literally a few weeks before I picked up this book. I have been through three Ivy League school classes that had it as an assigned reading, among others, and it was always the most superior reading. It starts from scratch, assumes no previous knowledge of machine learning, tech, or linguistics, and explains everything about these fields at a near perfect pace.
In my mind, the target audience of this book is complete NLP dummies - with the critical nuance that it is for dummies (like me) who wish to become experts. It's not a generic introduction, it doesn't give you a generalist's overview. It's a fairly technical textbook with all the algorithms and the sausage making of natural language AI, starting from its naive beginnings and up to state-of-the-art large language models. It does, however, guide you through this long journey gently, step-by-step, if you're willing to put-in the effort to follow along.
For a CompSci major, my guess is that this is an average introductory read. For the rest of us, it could be a fairly challenging and technical book. If you are seriously interested in the field, though, you will hardly find a better starting point. Forget about youtube video on transformers, they will just get you more confused. LLMs are an impressive invention that is contingent on a long chain of innovations, so you can never truly understand them without taking the full story / narrative in a long book format.
If this book made me appreciate anything, it's the amount of ingenuity that went into what became ChatGPT. It wasn't a single brilliant idea, but 70 years of brilliantly clever ideas that accumulated one after the other to deliver this mindblowing piece of technology. One thing remains very mind boggling to me after reading it: in spite of all the genius that went into compiling LLMs, everything I learned still hardly makes me belive that it is enough to make ChatGPT do the things it does.
February 5, 2023
It's a great book on NLP, written by leading researchers in the field. In general, I liked it but maybe it could be split into two books, i.e. fundamentals and applications and computational linguistics or something of the sort. Looking at the latest draft, I think Dan and James and heading in that direction already. In any case, this is the Bible of NLP and I strongly recommend at least the first twelve chapters to anyone who is interested in natural language processing.
P.S. One important note is that the field is currently in the midst of a scientific revolution and on the hype train (I'm looking at you ChatGPT), so new research papers come out literally every week. Although Dan and James are trying to keep up, it's not an easy task to do. For example, as I was reading the 2022 draft, the 2023 draft came out (on Jan. 7th). Of course, most of the fundamentals are unchanged but one should keep that in mind and make sure to always read the latest edition of the book (which can be found here: https://web.stanford.edu/~jurafsky/slp3/)
P.S. One important note is that the field is currently in the midst of a scientific revolution and on the hype train (I'm looking at you ChatGPT), so new research papers come out literally every week. Although Dan and James are trying to keep up, it's not an easy task to do. For example, as I was reading the 2022 draft, the 2023 draft came out (on Jan. 7th). Of course, most of the fundamentals are unchanged but one should keep that in mind and make sure to always read the latest edition of the book (which can be found here: https://web.stanford.edu/~jurafsky/slp3/)
August 20, 2020
I read this off and on over the past 6 months in self-study. I have a pretty decent math/computational background and like linguistics, but previously had no idea what computational linguistics encompassed, so my goal was to get a good survey of the field. This book was amazing at that - it introduced a ton of concepts, but introduced them clearly and in a well-organized, reader-friendly way.
The more technical sections often didn't have enough context or examples for me to understand properly (i.e. to be able to implement something myself). But it's understandable because this is an intro book, and the chapters always end with a summary of the topics and additional references. For the things that I was more interested in (syntax parsing, semantic parsing), it was easy to learn more deeply. For other sections, I just glossed over/skipped them. :|
The more technical sections often didn't have enough context or examples for me to understand properly (i.e. to be able to implement something myself). But it's understandable because this is an intro book, and the chapters always end with a summary of the topics and additional references. For the things that I was more interested in (syntax parsing, semantic parsing), it was easy to learn more deeply. For other sections, I just glossed over/skipped them. :|
May 9, 2024
Even not knowing so much of CS, this book brings me to state-of-the-art knowledge on NLP. I am amazed. It's not friendly, and I didn't understand big parts of the book because I don't have a CS background. But with some probability and maths knowledge it let me introduce in all the concepts. 3rd edition is free online and is amazing how updated it is, how real-time issues are treated. Chapters 10 and 11 are amazing for people trying to understand transformers and uni or bidirectional models.
Of course, more example can add simplicity for people like me. But I found it impressively comprehensive and funny. It's written in common language, not fancy but accurate. I was all what I was looking for, trying to understand NLP.
Of course, more example can add simplicity for people like me. But I found it impressively comprehensive and funny. It's written in common language, not fancy but accurate. I was all what I was looking for, trying to understand NLP.
May 15, 2024
I have read this book (3rd edition) as a textbook for my undergrad NLP course. This is a very well-written and well-explained book. To be more specific, I read the following topics for my course work, which helped me a lot to clear my concept about the topics.
ML essentials: 3.1, 3.2, 3.6.1. 4.1, 4.2, 4.3, 4.4, 4.5, 4.7, 4.8, 4.9 (excluding 4.9.1), 4.10.
Word representations: 6.1, 6.2, 6.3, 6.4, 6.5, 6.7, 6.9, 6.10, 6.11, 6.12, 6.8
Sequence learning: 8.1, 8.2, 8.3, 8.4
Neural Networks: 7.1, 7.2, 7.3, 7.4, 9.1, 9.3 (excluding 9.3.3), 9.4, 9.5, 9.6
Machine translation: 9.7, 9.8, 13.1, 13.2
ML essentials: 3.1, 3.2, 3.6.1. 4.1, 4.2, 4.3, 4.4, 4.5, 4.7, 4.8, 4.9 (excluding 4.9.1), 4.10.
Word representations: 6.1, 6.2, 6.3, 6.4, 6.5, 6.7, 6.9, 6.10, 6.11, 6.12, 6.8
Sequence learning: 8.1, 8.2, 8.3, 8.4
Neural Networks: 7.1, 7.2, 7.3, 7.4, 9.1, 9.3 (excluding 9.3.3), 9.4, 9.5, 9.6
Machine translation: 9.7, 9.8, 13.1, 13.2
August 2, 2019
The holy grail of Natural Language Processing. Includes state of the art algorithms and delves into subjects such as machine learning in detail despite not being it's main focus. It also includes plenty of automata theory which is it's basis for many of the algorithms presented.
Not an easy book by any means and if I had any complaint, is that it's extremely verbose and at the same time extremely technical. So in depth understanding of automata and math is required.
Definitely to read again.
Not an easy book by any means and if I had any complaint, is that it's extremely verbose and at the same time extremely technical. So in depth understanding of automata and math is required.
Definitely to read again.
February 4, 2018
In the words of one of my coworkers "That book is awesome!"
I first read this book in 2011 as a grad student, and still return to this resource on a weekly basis! Fantastic overview of NLP techniques.
I'm looking forward to the 3rd edition.
I first read this book in 2011 as a grad student, and still return to this resource on a weekly basis! Fantastic overview of NLP techniques.
I'm looking forward to the 3rd edition.
considering
December 5, 2018Recomendado en Natural Language Processing with Python como un texto más avanzado.
October 19, 2021
What a nice book to learn both (modern) Natural Language Processing and (computational) Linguistics. I am recommending this book for both undergraduate (but with high level of mathematics) and graduate students.
December 14, 2017
This book is good for fundamental understanding of NLP. But some area is not explained well here.
April 14, 2018
Exceptional work!
January 29, 2019
Great overview of different problems and methods in NLP. Gives a good sense of what the challenges are and the different existing areas under the NLP umbrella.
April 6, 2019
Incredible.
September 28, 2019
Roughly read.
Read
February 22, 2020This book was a big help to understand and introduce to the speech recognition for the natural language processing project I was working on it.
December 19, 2020
LOVED the references, one of the most entertaining textbooks I've been assigned - Prophetess Cassandra, The Pirates of Penzanse, Noam Chomsky, etc.
Displaying 1 - 30 of 51 reviews