Overview of natural language processing (NLP) from both symbolic and deep learning perspectives. Covers tf-idf, sentiment analysis, LDA, WordNet, FrameNet, word2vec, and recurrent neural networks (RNNs).
There are lots of frameworks for building chatbots, but those abstractions can obscure understanding and hinder application development. In this talk, we will cover building chatbots from the ground up in Python. This can be done with either classic NLP or deep learning. We will cover both approaches, but this talk will focus on how one can build a chatbot using spaCy, pattern matching, and context-free grammars.
Introduction to Natural Language ProcessingPranav Gupta
the presentation gives a gist about the major tasks and challenges involved in natural language processing. In the second part, it talks about one technique each for Part Of Speech Tagging and Automatic Text Summarization
Deep Learning for Natural Language ProcessingJonathan Mugan
Deep Learning represents a significant advance in artificial intelligence because it enables computers to represent concepts using vectors instead of symbols. Representing concepts using vectors is particularly useful in natural language processing, and this talk will elucidate those benefits and provide an understandable introduction to the technologies that make up deep learning. The talk will outline ways to get started in deep learning, and it will conclude with a discussion of the gaps that remain between our current technologies and true computer understanding.
There are lots of frameworks for building chatbots, but those abstractions can obscure understanding and hinder application development. In this talk, we will cover building chatbots from the ground up in Python. This can be done with either classic NLP or deep learning. We will cover both approaches, but this talk will focus on how one can build a chatbot using spaCy, pattern matching, and context-free grammars.
Introduction to Natural Language ProcessingPranav Gupta
the presentation gives a gist about the major tasks and challenges involved in natural language processing. In the second part, it talks about one technique each for Part Of Speech Tagging and Automatic Text Summarization
Deep Learning for Natural Language ProcessingJonathan Mugan
Deep Learning represents a significant advance in artificial intelligence because it enables computers to represent concepts using vectors instead of symbols. Representing concepts using vectors is particularly useful in natural language processing, and this talk will elucidate those benefits and provide an understandable introduction to the technologies that make up deep learning. The talk will outline ways to get started in deep learning, and it will conclude with a discussion of the gaps that remain between our current technologies and true computer understanding.
This lectures provides students with an introduction to natural language processing, with a specific focus on the basics of two applications: vector semantics and text classification.
(Lecture at the QUARTZ PhD Winter School (http://www.quartz-itn.eu/training/winter-school/ in Padua, Italy on February 12, 2018)
Natural Language Processing and Search Intent Understanding C3 Conductor 2019...Dawn Anderson MSc DigM
This talk looks at the ways in which search engines are evolving to understand further the nuance of linguistics in natural language processing and in understanding searcher intent.
Big Data and Natural Language ProcessingMichel Bruley
Natural Language Processing (NLP) is the branch of computer science focused on developing systems that allow computers to communicate with people using everyday language.
Grammarly AI-NLP Club #2 - Recent advances in applied chatbot technology - Jo...Grammarly
Speaker: Jordi Carrera Ventura, Artificial Intelligence technologist at Telefónica R&D
Summary: Chatbots (aka conversational agents, spoken dialogue systems) allow users to interface with computers using natural language by simply asking questions or issuing commands.
Given a query, the chatbot builds a semantic representation of the input, transforms it into a logical statement, and performs all the necessary actions to fulfill the user's intent. Sometimes this simply means calculating an exact answer or retrieving a fact from a database, whereas other times it means building a contextual model and running a full-fledged conversation flow while keeping track of anaphoras and cross-references.
Besides the direct applications of chatbots in IoT (Amazon’s Alexa, Apple's Siri) and IT (the historical field of Information Retrieval as a whole can be seen as a sub-problem of spoken dialogue systems), chatbots' main appeal for technologists is their location at the intersection of all major Natural Language Processing technologies and many of the deepest questions in Cognitive Science today: semantic parsing, entity recognition, knowledge representation, and coreference resolution.
In this talk, I will explore those questions in the context of an applied industry setting, and I will introduce a framework suitable for addressing them, together with an overview of the state-of-the-art in chatbot technology and some original techniques.
Dilek Hakkani-Tur at AI Frontiers: Conversational machines: Deep Learning for...AI Frontiers
In this talk, I will present recent developments in Google Research for end-to-end goal-oriented dialogue systems, with components for language understanding, dialogue state tracking, policy, and language generation. The talk will summarize novel aspects of each component, and highlight novel approaches where dialogue is viewed as a collaborative game between a user and an agent: The user has a goal in mind and the agent has access to the data that user is interested in, and can perform actions in order to realize the user’s goal. The two engage in a conversation so that the agent can help the user find a way for task completion.
What is BERT? It is Google's neural network-based technique for natural language processing (NLP) pre-training. BERT stands for Bidirectional Encoder Representations from Transformers. It was opened-sourced last year and written about in more detail on the Google AI blog. In this presentation we look at what Google BERT means for SEOs and marketers and how Google BERT is and will continue to impact the search landscape. We also look at the back story to Google BERT, including transformers and natural language understanding and computational linguistics.
2017 Tutorial - Deep Learning for Dialogue SystemsMLReview
In the past decade, goal-oriented spoken dialogue systems (SDS) have been the most promi-nent component in today’s virtual personal assistants (VPAs). Among these VPAs, Microsoft’s Cortana, Apple’s Siri, Amazon Alexa, Google Assistant, and Facebook’s M, have incorporated SDS modules in various devices, which allow users to speak naturally in order to finish tasks more efficiently. The traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applicatins of neural models to dialogue modeling. Nevertheless, applying deep learning technologies for building robust and scalable dialogue systems is still a challenging task and an open research area as it requires deeper understanding of the classic pipelines as well as detailed knowledge on the benchmark of the models of the prior work and the recent state-of-the-art work. Thus, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems, and summarizing the challenges. We target an audience of students and practitioners who have some deep learning background and want to get more familiar with conversational dialog systems.
Google BERT is many things, including the name of a Google Search algorithm update. There is lots of confusion as to what Google BERT is, where it has come from and what SEOs and marketers need to do about it (if anything). Here we look at the solutions the introduction of Google BERT by Google seeks to provide and explore the background to natural language processing and computational linguistics.
Presented by Ted Xiao at RobotXSpace on 4/18/2017. This workshop covers the fundamentals of Natural Language Processing, crucial NLP approaches, and an overview of NLP in industry.
Talk from Tech SEO Boost 2019 by Dawn Anderson on the move to the just in time predictive personalised search experience for search engines and users. Exploring recommender systems, collaborative filtering, temporal and location based queries and the rise of predictive, personal dynamic search. Exploring the work of information retrieval researchers and Google Discover.
DataFest 2017. Introduction to Natural Language Processing by Rudolf Eremyanrudolf eremyan
The objective of this workshop is to show how natural language processing applied in modern applications such as Google Search, Apple Siri, Bing Translator and etc. During the workshop we will go through history if natural language processing, talk about typical problems, consider classical approaches and methods, and compare them with state-of-the-art deep learning techniques.
Author: Rudolf Eremyan
Email: eremyan.rudolf@gmail.com
Phone: +995599607066
LinkedIn: https://www.linkedin.com/in/rudolferemyan/
DataFest Tbilisi 2017 website: https://datafest.ge
In 1971, David Parnas wrote the great paper, "On the criteria to be used decomposing the system into parts," and yet the problem of breaking down big projects into small parts that work well together remains a struggle in the industry. The ability to decompose a problem space and in turn, compose a solution is essential to our work.
Things have gotten worse since 1971. With microservices, big data, and streaming systems, we're all going to be distributed systems engineers sooner or later. In distributed systems, effective decomposition has an even greater impact on the reliability, performance, and availability of our systems as it determines the frequency and weight of communication in the system.
This talk speaks to the essential considerations for defining and evaluating boundaries and behaviors in large-scale distributed systems. It will touch on topics such as bulkhead design and architectural evolution.
This lectures provides students with an introduction to natural language processing, with a specific focus on the basics of two applications: vector semantics and text classification.
(Lecture at the QUARTZ PhD Winter School (http://www.quartz-itn.eu/training/winter-school/ in Padua, Italy on February 12, 2018)
Natural Language Processing and Search Intent Understanding C3 Conductor 2019...Dawn Anderson MSc DigM
This talk looks at the ways in which search engines are evolving to understand further the nuance of linguistics in natural language processing and in understanding searcher intent.
Big Data and Natural Language ProcessingMichel Bruley
Natural Language Processing (NLP) is the branch of computer science focused on developing systems that allow computers to communicate with people using everyday language.
Grammarly AI-NLP Club #2 - Recent advances in applied chatbot technology - Jo...Grammarly
Speaker: Jordi Carrera Ventura, Artificial Intelligence technologist at Telefónica R&D
Summary: Chatbots (aka conversational agents, spoken dialogue systems) allow users to interface with computers using natural language by simply asking questions or issuing commands.
Given a query, the chatbot builds a semantic representation of the input, transforms it into a logical statement, and performs all the necessary actions to fulfill the user's intent. Sometimes this simply means calculating an exact answer or retrieving a fact from a database, whereas other times it means building a contextual model and running a full-fledged conversation flow while keeping track of anaphoras and cross-references.
Besides the direct applications of chatbots in IoT (Amazon’s Alexa, Apple's Siri) and IT (the historical field of Information Retrieval as a whole can be seen as a sub-problem of spoken dialogue systems), chatbots' main appeal for technologists is their location at the intersection of all major Natural Language Processing technologies and many of the deepest questions in Cognitive Science today: semantic parsing, entity recognition, knowledge representation, and coreference resolution.
In this talk, I will explore those questions in the context of an applied industry setting, and I will introduce a framework suitable for addressing them, together with an overview of the state-of-the-art in chatbot technology and some original techniques.
Dilek Hakkani-Tur at AI Frontiers: Conversational machines: Deep Learning for...AI Frontiers
In this talk, I will present recent developments in Google Research for end-to-end goal-oriented dialogue systems, with components for language understanding, dialogue state tracking, policy, and language generation. The talk will summarize novel aspects of each component, and highlight novel approaches where dialogue is viewed as a collaborative game between a user and an agent: The user has a goal in mind and the agent has access to the data that user is interested in, and can perform actions in order to realize the user’s goal. The two engage in a conversation so that the agent can help the user find a way for task completion.
What is BERT? It is Google's neural network-based technique for natural language processing (NLP) pre-training. BERT stands for Bidirectional Encoder Representations from Transformers. It was opened-sourced last year and written about in more detail on the Google AI blog. In this presentation we look at what Google BERT means for SEOs and marketers and how Google BERT is and will continue to impact the search landscape. We also look at the back story to Google BERT, including transformers and natural language understanding and computational linguistics.
2017 Tutorial - Deep Learning for Dialogue SystemsMLReview
In the past decade, goal-oriented spoken dialogue systems (SDS) have been the most promi-nent component in today’s virtual personal assistants (VPAs). Among these VPAs, Microsoft’s Cortana, Apple’s Siri, Amazon Alexa, Google Assistant, and Facebook’s M, have incorporated SDS modules in various devices, which allow users to speak naturally in order to finish tasks more efficiently. The traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applicatins of neural models to dialogue modeling. Nevertheless, applying deep learning technologies for building robust and scalable dialogue systems is still a challenging task and an open research area as it requires deeper understanding of the classic pipelines as well as detailed knowledge on the benchmark of the models of the prior work and the recent state-of-the-art work. Thus, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems, and summarizing the challenges. We target an audience of students and practitioners who have some deep learning background and want to get more familiar with conversational dialog systems.
Google BERT is many things, including the name of a Google Search algorithm update. There is lots of confusion as to what Google BERT is, where it has come from and what SEOs and marketers need to do about it (if anything). Here we look at the solutions the introduction of Google BERT by Google seeks to provide and explore the background to natural language processing and computational linguistics.
Presented by Ted Xiao at RobotXSpace on 4/18/2017. This workshop covers the fundamentals of Natural Language Processing, crucial NLP approaches, and an overview of NLP in industry.
Talk from Tech SEO Boost 2019 by Dawn Anderson on the move to the just in time predictive personalised search experience for search engines and users. Exploring recommender systems, collaborative filtering, temporal and location based queries and the rise of predictive, personal dynamic search. Exploring the work of information retrieval researchers and Google Discover.
DataFest 2017. Introduction to Natural Language Processing by Rudolf Eremyanrudolf eremyan
The objective of this workshop is to show how natural language processing applied in modern applications such as Google Search, Apple Siri, Bing Translator and etc. During the workshop we will go through history if natural language processing, talk about typical problems, consider classical approaches and methods, and compare them with state-of-the-art deep learning techniques.
Author: Rudolf Eremyan
Email: eremyan.rudolf@gmail.com
Phone: +995599607066
LinkedIn: https://www.linkedin.com/in/rudolferemyan/
DataFest Tbilisi 2017 website: https://datafest.ge
In 1971, David Parnas wrote the great paper, "On the criteria to be used decomposing the system into parts," and yet the problem of breaking down big projects into small parts that work well together remains a struggle in the industry. The ability to decompose a problem space and in turn, compose a solution is essential to our work.
Things have gotten worse since 1971. With microservices, big data, and streaming systems, we're all going to be distributed systems engineers sooner or later. In distributed systems, effective decomposition has an even greater impact on the reliability, performance, and availability of our systems as it determines the frequency and weight of communication in the system.
This talk speaks to the essential considerations for defining and evaluating boundaries and behaviors in large-scale distributed systems. It will touch on topics such as bulkhead design and architectural evolution.
Talk given at the 6th Irish NLP Meetup on query understanding using conceptual slices and word embeddings.
https://www.meetup.com/NLP-Dublin/events/237998517/
Computational Creativity is the scientific study of the creative potential of machines: to determine whether machines can indeed be creative, it aims to build generative machines and programs that exhibit human-scale creativity.
Creative Twitterbots are software agents that have their own world views, formulate their own opinions and tweet their own original messages. This Tutorial considers what it means for a text to be creative, briefly surveys the emerging technology of Twitterbots, and describes the workings of a creative metaphor-generating Twitterbot called @MetaphorMagnet
Chatbots are growing in popularity as developers face the
limitations of the mobile app. User interfaces that simulate a human
conversation, the history of chatbots goes back to the late 18th
century. I'll take you on a tour of that history with an eye on finding
insights on what is possible today and in the near future with chatbots.
Issues Covered: Amazon Alexa, Facebook Messenger Chatbots, Alan
Turing, and much more.
slides from my recent presentation to the Malaysian Higher Education conference in Langkawi on March 1st, 2007. See blog posting at www.autodesk.com/waynehodgins
Different Kinds Of Essay. 8 Types of Essays in College: All You Need to Know ...Sara Carter
What Is an Essay? Different Types of Essays with Examples • 7ESL. Custom Writing of All Types of Essays. 4 Major types of essays - Infographics. 4 Essay Types and How to Distinguish Them | Howtowrite.CustomWritings.com. A complete Guide for Essay writing. 4 Outstanding Types of Essay Writing Styles – Helpful Guidelines. Tips on How to Write Effective Essay and 7 Major Types in 2021 | Types .... What Are The Different Types Of Essay Writing – Telegraph. The Major Types of Essays | CustomEssayMeister.com. an argument paper with two different types of writing and the same type .... 8 Types of Essays in College: All You Need to Know about College Essay .... Types of Essays Australian College Students Ask for (5 PhD Experts ....
Midwest km pugh conversational ai and ai for conversation 190809Katrina (Kate) Pugh
Conversational AI (chat bots) is here to stay, and it's teaching us a lot about transactions, human language patterns, and the limits of computer-human interaction. But what about AI for Conversation? Can we learn from the Conversational AI research and improve how human-to-human conversation works? Where can we use pattern recognition and predictive analytics to improve how we are present as managers, coaches, analysts, family members or diplomats?
With Fashion Week to inspire us, this webinar focuses on sharing a few favorite digital trends for 2018. Instead of discussing denim separates and art-inspired prints, our team explores hot digital to keep an eye on. The webinar focuses on emerging technologies, exciting design trends and standout digital strategies to adopt in the new year.
Associate Creative Director Jessica DeJong and Chief Strategist Kalev Peekna dive into concepts that could disrupt how we think about digital experiences, as well as trends to easily fold into your 2018 marketing strategy.
Access the full recording: https://youtu.be/N_4XAsXDoYI
Similar to From Natural Language Processing to Artificial Intelligence (20)
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
Data Centers - Striving Within A Narrow Range - Research Report - MCG - May 2...pchutichetpong
M Capital Group (“MCG”) expects to see demand and the changing evolution of supply, facilitated through institutional investment rotation out of offices and into work from home (“WFH”), while the ever-expanding need for data storage as global internet usage expands, with experts predicting 5.3 billion users by 2023. These market factors will be underpinned by technological changes, such as progressing cloud services and edge sites, allowing the industry to see strong expected annual growth of 13% over the next 4 years.
Whilst competitive headwinds remain, represented through the recent second bankruptcy filing of Sungard, which blames “COVID-19 and other macroeconomic trends including delayed customer spending decisions, insourcing and reductions in IT spending, energy inflation and reduction in demand for certain services”, the industry has seen key adjustments, where MCG believes that engineering cost management and technological innovation will be paramount to success.
MCG reports that the more favorable market conditions expected over the next few years, helped by the winding down of pandemic restrictions and a hybrid working environment will be driving market momentum forward. The continuous injection of capital by alternative investment firms, as well as the growing infrastructural investment from cloud service providers and social media companies, whose revenues are expected to grow over 3.6x larger by value in 2026, will likely help propel center provision and innovation. These factors paint a promising picture for the industry players that offset rising input costs and adapt to new technologies.
According to M Capital Group: “Specifically, the long-term cost-saving opportunities available from the rise of remote managing will likely aid value growth for the industry. Through margin optimization and further availability of capital for reinvestment, strong players will maintain their competitive foothold, while weaker players exit the market to balance supply and demand.”
Show drafts
volume_up
Empowering the Data Analytics Ecosystem: A Laser Focus on Value
The data analytics ecosystem thrives when every component functions at its peak, unlocking the true potential of data. Here's a laser focus on key areas for an empowered ecosystem:
1. Democratize Access, Not Data:
Granular Access Controls: Provide users with self-service tools tailored to their specific needs, preventing data overload and misuse.
Data Catalogs: Implement robust data catalogs for easy discovery and understanding of available data sources.
2. Foster Collaboration with Clear Roles:
Data Mesh Architecture: Break down data silos by creating a distributed data ownership model with clear ownership and responsibilities.
Collaborative Workspaces: Utilize interactive platforms where data scientists, analysts, and domain experts can work seamlessly together.
3. Leverage Advanced Analytics Strategically:
AI-powered Automation: Automate repetitive tasks like data cleaning and feature engineering, freeing up data talent for higher-level analysis.
Right-Tool Selection: Strategically choose the most effective advanced analytics techniques (e.g., AI, ML) based on specific business problems.
4. Prioritize Data Quality with Automation:
Automated Data Validation: Implement automated data quality checks to identify and rectify errors at the source, minimizing downstream issues.
Data Lineage Tracking: Track the flow of data throughout the ecosystem, ensuring transparency and facilitating root cause analysis for errors.
5. Cultivate a Data-Driven Mindset:
Metrics-Driven Performance Management: Align KPIs and performance metrics with data-driven insights to ensure actionable decision making.
Data Storytelling Workshops: Equip stakeholders with the skills to translate complex data findings into compelling narratives that drive action.
Benefits of a Precise Ecosystem:
Sharpened Focus: Precise access and clear roles ensure everyone works with the most relevant data, maximizing efficiency.
Actionable Insights: Strategic analytics and automated quality checks lead to more reliable and actionable data insights.
Continuous Improvement: Data-driven performance management fosters a culture of learning and continuous improvement.
Sustainable Growth: Empowered by data, organizations can make informed decisions to drive sustainable growth and innovation.
By focusing on these precise actions, organizations can create an empowered data analytics ecosystem that delivers real value by driving data-driven decisions and maximizing the return on their data investment.
From Natural Language Processing to Artificial Intelligence
1. From Natural Language Processing
to Artificial Intelligence
Jonathan Mugan, PhD
@jmugan
Data Day Texas
January 14, 2017
2. “ It is not my aim to surprise or shock you – but the simplest way I
can summarize is to say that there are now in the world machines
that think, that learn and that create. Moreover, their ability to do
these things is going to increase rapidly until – in a visible future –
the range of problems they can handle will be coextensive with the
range to which the human mind has been applied. ”
3. “ It is not my aim to surprise or shock you – but the simplest way I
can summarize is to say that there are now in the world machines
that think, that learn and that create. Moreover, their ability to do
these things is going to increase rapidly until – in a visible future –
the range of problems they can handle will be coextensive with the
range to which the human mind has been applied. ”
Herbert Simon, 1957
4. “ It is not my aim to surprise or shock you – but the simplest way I
can summarize is to say that there are now in the world machines
that think, that learn and that create. Moreover, their ability to do
these things is going to increase rapidly until – in a visible future –
the range of problems they can handle will be coextensive with the
range to which the human mind has been applied. ”
Herbert Simon, 1957
So what is going on here?
There is no actual
understanding.
AI has gotten smarter
• especially with deep
learning, but
• computers can’t read or
converse intelligently
5. This is disappointing because we want to
• Interact with our world using natural language
• Current chatbots are an embarrassment
• Have computers read all those documents out there
• So they can retrieve the best ones, answer our
questions, and summarize what is new
6. To understand language, computers need to
understand the world
Why can you pull a wagon with a string but not push it? -- Minsky
Why is it unusual that a gymnast competed with one leg? -- Schank
Why does it only rain outside?
If a book is on a table, and you push the table, what happens?
If Bob went to the junkyard, is he at the airport?
They need to be able to answer questions like:
7. Grounded Understanding
• We understand language in a way that is grounded in sensation and action.
sensation representation action
• When someone says “chicken,” we map that to our experience with chickens.
• We understand each other because we have had similar experiences.
• This is the kind of understanding that computers need.
See: Benjamin Bergen, Steven Pinker,
Mark Johnson, Jerome Feldman, and
Murray Shanahan
“chicken”
11. Bag-of-words representation
“The aardvark ate the zoo.” = [1,0,1, ..., 0, 1]
We can do a little better and count how often the words occur.
tf: term frequency, how often does the word occur.
“The aardvark ate the aardvark by the zoo.” = [2,0,1, ..., 0, 1]
Treat words as arbitrary symbols and look at their frequencies.
“dog bit man” will be the same as “man bit dog”
Consider a vocabulary of 50,000 words where:
• “aardvark” is position 0
• “ate” is position 2
• “zoo” is position 49,999
A bag-of-words can be a vector with 50,000 dimensions.
12. Give rare words a boost
We can get fancier and say that rare words are more important than
common words for characterizing documents.
Multiply each entry by a measure of how common it is in the corpus.
idf: inverse document frequency
idf( term, document) = log(num. documents / num. with term)
Called a vector space model. You can throw these
vectors into any classifier, or find similar documents
based on similar vectors.
10 documents, only 1 has “aardvark” and 5 have “zoo” and 5 have “ate”
tf-idf: tf * idf
“The aardvark ate the aardvark by the zoo.” =[4.6,0,0.7, ..., 0, 0.7]
13. Topic Modeling (LDA)
Latent Dirichlet Allocation
• You pick the number of topics
• Each topic is a distribution over words
• Each document is a distribution over topics
Easy to do in gensim
https://radimrehurek.com/gensim/models/ldamodel.html
14. LDA of my tweets shown in pyLDAvis
I sometimes
tweet about
movies.
https://github.com/bmabey/pyLDAvis
15. Sentiment analysis: How the author feels about the text
Sentiment dictionary: word list with
sentiment values associated with all words
that might indicate sentiment
...
happy: +2
...
joyful: +2
...
pain: -3
painful: -3
...
We can do sentiment analysis using labeled data and meaningless
tokens, with supervised learning over tf-idf.
We can also do sentiment analysis by
adding the first hint of meaning: some
words are positive and some words are
negative.
One such word list is VADER https://github.com/cjhutto/vaderSentiment
“I went to the junkyard and was happy to see joyful people.”
17. Manually Constructing Representations
We tell the computer what
things mean by manually
specifying relationships between
symbols
1. Stores meaning using
predefined relationships
2. Maps multiple ways of
writing something to the
same representation
Allows us to code
what the machine
should do for a
relatively small
number of
representations
18. Manually Constructing Representations
vehicle
Honda
Civic
tires
is_ahas
Who might be in the market
for tires?
Allows us to code
what the machine
should do for a
relatively small
number of
representations
We tell the computer what
things mean by manually
specifying relationships between
symbols
1. Stores meaning using
predefined relationships
2. Maps multiple ways of
writing something to the
same representation
19. Manually Constructing Representations
vehicle
“... the car ...”
“... an automobile ...”
“... my truck ...”
Honda
Civic
“... cruising in my civic ...”
tires
is_ahas
Who might be in the market
for tires?
Allows us to code
what the machine
should do for a
relatively small
number of
representations
We tell the computer what
things mean by manually
specifying relationships between
symbols
1. Stores meaning using
predefined relationships
2. Maps multiple ways of
writing something to the
same representation
22. FrameNet
• More integrative than WordNet: represents situations
• One example is a child’s birthday party, another is Commerce_buy
• situations have slots (roles) that are filled
• Frames are triggered by keywords in text (more or less)
FrameNet: https://framenet.icsi.berkeley.edu/fndrupal/IntroPage
Commerce_buy: https://framenet2.icsi.berkeley.edu/fnReports/data/frameIndex.xml?frame=Commerce_buy
Commerce_buy triggered by the words: buy,
buyer, client, purchase, or purchaser
Roles: Buyer, Goods,
Money, Place (where
bought), ...
Commerce_buy
Getting
Inherits from
Commerce_buy indicates a change of possession, but we need
a world model to actually change a state.
24. YAGO: Yet Another Great Ontology
• Built on WordNet and DBpedia
• http://www.mpi-inf.mpg.de/departments/databases-and-
information-systems/research/yago-naga/yago/
• DBpedia has a machine readable page for each Wikipedia
page
• Used by IBM Watson to play Jeopardy!
• Big on named entities, like entertainers
• Browse
• https://gate.d5.mpi-inf.mpg.de/webyago3spotlx/Browser
25. SUMO: Suggested Upper Merged Ontology
There is also YAGO-SUMO that merges the low-
level organization of SUMO with the instance
information of YAGO.http://people.mpi-
inf.mpg.de/~gdemelo/yagosumo/
Deep: organizes concepts down to the lowest level
http://www.adampease.org/OP/
Example: cooking is a type of making that is a type
of intentional process that is a type of process that
is a physical thing that is an entity.
26. Image Schemas
Humans use image schemas comprehend spatial
arrangements and movements in space [Mandler, 2004]
Examples of image schemas include path, containment,
blockage, and attraction [Johnson, 1987]
Abstract concepts such as romantic relationships and
arguments are represented as metaphors to this kind of
experience [Lakoff and Johnson, 1980]
Image schemas are representations of human experience
that are common across cultures [Feldman, 2006]
27. Semantic Web (Linked Data)
• Broad, but not
organized or deep
• Way too complicated
• May eventually be
streamlined (e.g.
JSON-LD), and it could
be very cool if it gets
linked with deeper,
better organized data
• Tools to map text:
• FRED
• DBpedia Spotlight
• Pikes
Semantic Web Layer Cake Spaghetti Monster
29. World models
Computers need causal models of how the world works
and how we interact with it.
• People don’t say everything to get a message across,
just what is not covered by our shared conception
• Most efficient way to encode our shared conception is
a model
Models express how the world changes based on events
• Recall the Commerce_buy frame
• Afterward, one person has more money and another
person has less
• Read such inferences right off the model
30. Dimensions of models
• Probabilistic
• Deterministic compared with stochastic
• E.g., logic compared with probabilistic programming
• Factor state
• whole states compared with using variables
• E.g., finite automata compared with dynamic Bayesian networks
• Relational
• Propositional logic compared with first-order logic
• E.g., Bayesian networks compared with Markov logic networks
• Concurrent
• Model one thing compared with multiple things
• E.g., finite automata compared with Petri Nets
• Temporal
• Static compared with dynamic
• E.g., Bayesian networks compared with dynamic Bayesian
networks
32. Merge representations with models
Explain your conception of
conductivity?
Electrons are small spheres, and
electricity is small spheres going
through a tube. Conductivity is how
little blockage is in the tube.
Cyc has a model that uses
representations, but it is not clear if
logic is sufficiently supple.
Why does it only rain outside?
A roof blocks the path of things
from above.
The meaning of the word
“chicken” is everything explicitly
stated in the representation and
everything that can be inferred
from the world model.
“chicken”
The final step on this path is to
create a robust model around
rich representations.
37. word2vec
The word2vec model learns a vector for each
word in the vocabulary.
The number of dimensions for each word vector is
the same and is usually around 300.
Unlike the tf-idf vectors, word vectors are dense,
meaning that most values are not 0.
38. word2vec
1. Initialize each word with a random vector
2. For each word w1 in the set of documents:
3. For each word w2 around w1:
4. Move vectors for w1 and w2 closer
together and move all others and w1
farther apart
5. Goto 2 if not done
• Skip-gram model [Mikolov et al., 2013]
• Note: there are really two vectors per word, because you don’t want a word to
be likely to be around itself, see Goldberg and
Levyhttps://arxiv.org/pdf/1402.3722v1.pdf
• First saw that double-for-loop explanation from Christopher Moody
39. word2vec meaning
“You shall know a word by the company it keeps.” J. R. Firth [1957]
The quote we often see:
This seems at least kind of true.
• Vectors have internal structure [Mikolov et al., 2013]
• Italy – Rome = France – Paris
• King – Queen = Man – Woman
But ... words aren’t grounded in experience; they are only
grounded in being around other words.
Can also do word2vec on ConceptNet, see https://arxiv.org/pdf/1612.03975v1.pdf
41. seq2seq model
The seq2seq (sequence-to-sequence) model can encode
sequences of tokens, such as sentences, into single
vectors.
It can then decode these vectors into other sequences
of tokens.
Both the encoding and decoding are done using
recurrent neural networks (RNNs).
One obvious application for this is machine translation.
For example, where the source sentences are English
and the target sentences are Spanish.
45. Encoding sentence meaning into a vector
Like a hidden Markov model, but doesn’t make the Markov
assumption and benefits from a vector representation.
h0
The
h1
patient
h2
fell
h3
.
“The patient fell.”
49. Decoding sentence meaning
Machine translation, or structure learning more generally.
El
h3
paciente
h4
cayó
h5
.
h5
[Cho et al., 2014]
It keeps generating until it generates a stop symbol. Note that the lengths don’t
need to be the same. It could generate the correct “se cayó.”
• Treats this task like it is devoid of meaning.
• Great that this can work on just about any kind of seq2seq
problem, but this generality highlights its limitation for use
as language understanding. No Chomsky universal grammar.
53. Deep learning and question answering
RNNs answer questions.
What is the translation of this
phrase to French?
What is the next word?
Attention is useful for question
answering.
This can be generalized to which facts
the learner should pay attention to
when answering questions.
54. Deep learning and question answering
Bob went home.
Tim went to the junkyard.
Bob picked up the jar.
Bob went to town.
Where is the jar? A: town
• Memory Networks [Weston et al.,
2014]
• Updates memory vectors based on
a question and finds the best one to
give the output.
The office is north of the yard.
The bath is north of the office.
The yard is west of the kitchen.
How do you go from the office to
the kitchen? A: south, east
• Neural Reasoner [Peng et al.,
2015]
• Encodes the question and facts in
many layers, and the final layer is
put through a function that gives
the answer.
55. Deep learning and question answering
The network is learning linkages between sequences
of symbols, but these kinds of stories do not have
sufficiently rich linkages to our world.
57. External world training
If we want to talk to machines
1. We need to train them in an environment as much like our
own as possible
2. Can’t just be dialog!
Harnad [1990] http://users.ecs.soton.ac.uk/harnad/Papers/Harnad/harnad90.sgproblem.html
To understand “chicken” we need the machine
to have had as much experience with chickens
as possible.
When we say “chicken” we don’t just mean the
bird, we mean everything one can do with it
and everything it represents in our culture.“chicken”
58. There has been work in this direction
Industry
• OpenAI
• Universe: train on screens with VNC
• Now with Grand Theft Auto!
https://openai.com/blog/GTA-V-plus-Universe/
• Google
• Mikolov et al., A Roadmap towards
Machine Intelligence. They define an
artificial environment.
https://arxiv.org/pdf/1511.08130v2.pdf
• Facebook
• Weston, memory networks to dialogs
https://arxiv.org/pdf/1604.06045v7.pdf
• Kiela et al., Virtual Embodiment: A
Scalable Long-Term Strategy for
Artificial Intelligence Res. Advocate
using video games “with a purpose.”
https://arxiv.org/pdf/1610.07432v1.pdf
Academia
• Ray Mooney
• Maps text to situations
http://videolectures.net/aaai2013_moo
ney_language_learning/
• Luc Steels
• Robots come up with
vocabulary and simple grammar
• Narasimhan et al.
• Train a neural net to play text-
based adventure games
https://arxiv.org/pdf/1506.08941v2.pdf
iCub
59. But we need more training centered in our world
Maybe if Amazon Alexa had a camera and
rotating head?
How far could we get without the benefit of a
teacher?
• Could we use eye gaze as a cue? [Yu and
Ballard, 2010]
63. sensation representation action
Final thought
Open problem: What is the simplest commercially viable
task that requires commonsense knowledge and
reasoning?
AI has gotten a lot smarter, in recent years, especially with the benefits of deep learning, but natural language understanding is still lacking.
Computers must understand our world to understand language.
We don’t understand our biological structure, so we can’t just copy it in software, and we don’t know how to implement an alternative structure with equivalent capabilities, so we employ a bunch of parlor tricks to get us close to what we want. This is the field of natural language processing.
For sub-symbolic PDP original book and pep at 25.
For sub-symbolic pep original book and pep at 25.
For sub-symbolic pep original book and pep at 25.
There is some indirect meaning based on how people use symbols together.
In real writing you have a thesis, a central thing to to say. A predicate.
There is some indirect meaning based on how people use symbols together.
In real writing you have a thesis, a central thing to to say. A predicate.
For sub-symbolic pep original book and pep at 25.
A set of meanings where each one is a set of sense entities called synsets.
A set of meanings where each one is a set of sense entities called synsets.
Frames are more integrative; they represent more kinds of relationships between concepts, and those relationships are situation specific, so in a sense the representation is richer. However, Commerce_buy doesn’t say that one person owns something and
now has less money (confirm this).
For sub-symbolic PDP original book and pep at 25.
Should I say they are causal models? We want causal because we want to know how the system would behave in new situations. Causality is what happens if there is an exogenous change.
Compare
I flipped the light switch. the light will go on.
2. I made the rooster crow. the sun will not rise.
For sub-symbolic pep original book and pep at 25.
For sub-symbolic PDP original book and PDP at 25.
Should “happy” and “sad” have similar vectors when they are, in a sense, opposite?