Natural Language Understanding

Not Chatbots

{
            "intent": "agent.acquaintance",
            "utterances": [
              "say about you",
              "why are you here",
              "what is your personality",
              "describe yourself",
              "tell me about yourself",
              "tell me about you",
              "what are you",
              "who are you",
              "I want to know more about you",
              "talk about yourself"
            ],
            "answers": [
              "I'm a virtual agent",
              "Think of me as a virtual agent",
              "Well, I'm not a person, I'm a virtual agent",
              "I'm a virtual being, not a real person",
              "I'm a conversational app"
            ]
          },
          {
            "intent": "agent.age",
            "utterances": [
              "your age",
              "how old is your platform",
              "how old are you",
              "what's your age",
              "I'd like to know your age",
              "tell me your age"
            ],
            "answers": [
              "I'm very young",
              "I was created recently",
              "Age is just a number. You're only as old as you feel"
            ]
          }
Natural Language Processing in the Browser

Statistical NLP

Translation, named entity recognition, sentiment analysis, intent recognition

Train on large dataset of text pairs

In “Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges” and follow-up papers [4,5,6,7], we push the limits of research on multilingual NMT by training a single NMT model on 25+ billion sentence pairs, from 100+ languages to and from English, with 50+ billion parameters. 
Exploring Massively Multilingual, Massive Neural Machine Translation "

Classical Syntactic Systems

Parse Trees

Semantic forms

Some NLU data points

Recap on NLP

Typical NLP tasks:

  • Sentiment analysis
  • Named entity recognition
  • Classification: e.g., spam detection
  • Summarization
  • Machine translation

Semantic / episodic knowledge not involved at all

Episodic Memory

Toy Memory

NLU as memory search