Lecture 1 Introduction
Lecture 1 Introduction
Processing
Working on LLM+Vision
https://www.deeplearningbook.org/
• What is NLP?
• A Not So Brief History of NLP
 Qwen-72B-T:
 The goal of Natural Language Processing (NLP) is to enable computers to understand, interpret,
   and generate human language in a way that is both accurate and contextually meaningful….
Gemini-1.5-Pro-Search:
The ultimate goal of Natural Language Processing (NLP) is to enable computers to comprehend and
interact with human language as effectively as humans do. [1][2] …
 LLMs all agree that understand, interpret and generate are the tasks.
 They use very ambiguous terms in terms of evaluation.
 What is meaningful/useful? How can we know?
What is Natural Language Processing?
Me: What is the goal of natural language processing?
Llama-3.1-405B-T:
  The primary goal of Natural Language Processing (NLP) is to enable computers to understand,
interpret, and generate human language, allowing humans and machines to communicate effectively
and efficiently.
NLP aims to bridge the gap between human language and computer language, enabling computers to:
Understand human language: NLP helps computers to comprehend the meaning of text or speech,
including grammar, syntax, semantics, and pragmatics.
Interpret human language: NLP enables computers to extract relevant information, identify patterns,
and make inferences from text or speech.
Generate human language: NLP allows computers to produce human-like text or speech, such as
chatbots, language translation systems, and text summarization tools.
                                         Formal
                                        Language
                                          (code)
                                        Generate                          Formal
     Natural                                                             Language
    Language                                                              (execution
                                                                            result)
What is Natural Language Processing?
Me: What is the goal of natural language processing?
Llama-3.1-405B-T:
  The primary goal of Natural Language Processing (NLP) is to enable computers to understand,
interpret, and generate human language, allowing humans and machines to communicate effectively
and efficiently.
NLP aims to bridge the gap between human language and computer language, enabling computers to:
                                       Formal
                                      Language
                                         (code)
                                       Generate                       Formal
     Natural                                                         Language
    Language                                                          (execution
                                                                        result)
What is Natural Language Processing?
                                   Formal
                                  Language
                                     (code)
                                  Generate                       Formal
      Natural                                                   Language
     Language                                                    (execution
                                                                   result)
Understand
or
                                  Natural                                      Natural
                                 Language                                     Language
                                                     Generate
What is Natural Language Processing?
Llama-3.1-405B-T:
  The primary goal of Natural Language Processing (NLP) is to enable computers to understand,
interpret, and generate human language, allowing humans and machines to communicate effectively
and efficiently.
NLP aims to bridge the gap between human language and computer language, enabling computers to:
Understand human language: NLP helps computers to comprehend the meaning of text or speech,
including grammar, syntax, semantics, and pragmatics.
Interpret human language: NLP enables computers to extract relevant information, identify patterns,
and make inferences from text or speech.
Generate human language: NLP allows computers to produce human-like text or speech, such as
chatbots, language translation systems, and text summarization tools.
Do you think that current (or in a very near future) NLP system can Understand human language?
Do you think that current (or in a very near future) NLP system can Interpret human language?
Do you think that current (or in a very near future) NLP system can Generate human language?
                                                                               Claude Shannon
                                                                               1919-2001
                                                                               " I visualize a time when we will be to robots
             Prediction and Entropy of Printed English, 1950, Claude Shannon   what dogs are to humans. And I am rooting
                                                                               for the machines"
                                                                             Claude Shannon
                                                                             1919-2001
                                                                             " I visualize a time when we will be to robots
           Prediction and Entropy of Printed English, 1950, Claude Shannon   what dogs are to humans. And I am rooting
                                                                             for the machines "
Rules:
S → NP VP
NP → Det Nominal
Nominal → Noun | Nominal PP
VP → VP PP | Verb NP
PP → Preposition NP
Context-Free Grammar
A Brief History of NLP
AI winter
US funding of Machine Translation research was reckoned to have cost the public purse $20 million
 by the mid 1960s. The Automatic Language Processing Advisory Committee (ALPAC) produced a
 report on the results of the funding and concluded that "there had been no machine translation of
 general scientific text, and none is in immediate prospect". US funding for machine translation
 was stopped, and this had the effect of halting most associated work in non-Machine Translation
 NLP.
Due to lack of funding, much of work in NLP came from the computational linguistics during the AI
 winter.
A Brief History of NLP
                                                               Charles J. Fillmore
                                                               1929-2014
                                                         Richard Montague
                                                         1930-1971
                                                         "There is in my opinion no
                                                         important theoretical
                                                         difference between natural
                                                         languages and the artificial
                                                         languages of logicians "
                                                                    Mark Steedman
                                                                    1946-now
Compare this list with goals of NLP (understand, interpret and generate)
                                            This experimental
                                            system established
                                            the statistical
                                            principle of NLP.
                                            An early paper in
                                            1975, “Design of a       Fred Jelinek
                                            Linguistic Statistical   1932-2010
                                            Decoder for the
                                            Recognition of           "Every time I fire a linguist,
                                            Continuous Speech”       the performance of the
                                            by F. Jelinek, L.        speech recognizer goes up "
                                            Bahl, R. Mercer
                                            developed the            " Some of My Best Friends
                                            hidden Markov            Are Linguists "
                                            model idea for
                                            speech.
A Brief History of NLP
Peter Brown and others at IBM finally developed the first statistical
MT system in 1988, “A statistical approach to language translation”.
                                                          Jürgen Schmidhuber
                                                          1963-Now
Yoshua Bengio and others developed the first neural language model
in 2000, “A Neural Probabilistic Language Model ”.
                                                                     Yoshua Bengio
                                                                     1964-Now
Tomáš Mikolov and others developed the first working neural word
representations, “Efficient Estimation of Word Representations in
Vector Space”.
                                                                    Tomáš Mikolov
                                                                    1982-Now
                                                               Geoffrey Hinton
                                                               1947-Now
This is the first work that shows, language model alone can solve
multiple tasks.
“ In fact, its only achievement is to use up a lot of California’s energy. You can’t go to a physics
conference and say: I’ve got a great theory. It accounts for everything and is so simple it can be
captured in two words: “Anything goes.” ” - Noam Chomsky
"Don't work on LLM. This is in the hands of large companies, there's nothing you can bring to the
table. You should work on next-gen AI systems that lift the limitations of LLMs. “ – Yann Lecun
What you will learn and why