Chatbots and AI
11 likes9,301 views
The document discusses different types of chatbots and how artificial intelligence can be used to power them. It covers topics like scripted chatbots versus more advanced bots using techniques like natural language understanding and machine learning. The document also examines word embeddings, an important technique for representing words as numeric vectors that has helped advance natural language processing and chatbots. It provides examples of how embeddings can be used for tasks like intent classification, entity recognition, determining word similarity and analogy.
![ENTITY RECOGNITION
Do you know a good vietnamese restaurant?
{restaurant_types: [italian french, japanese]}
{restaurant_type: vietnamese}](https://image.slidesharecdn.com/chatbotsandai-170312085910/85/Chatbots-and-AI-24-320.jpg)
Chatbots and AI
- 2. ARE ALL CHATBOTS CREATED EQUAL?
- 3. NOT WHAT CONVERSATION IS ABOUT SCRIPTED CHATBOTS
- 4. A BIT DECEPTIVE SO FAR? AI BOTS Vertical vs Horizontal bots
- 5. IT’S NOT ABOUT DEEP LEARNING ONLY AI ML NLP DL Expert systems Grammars ARTIFICIAL INTELLIGENCE ACHIEVEMENTS RL
- 6. ANATOMY OF A BOT Natural Language Under- standing “I haven’t received my shoes I ordered last week” Intent: Delivery problem Product: Shoes Date: Last_week INPUT Dialog system Business logic TRANSFORMATION INTO STRUCTURED DATA Action: Indicate delivery status Delivery date: Tomorrow Reason for delay: Shortage Natural language generation Parse the input of the user to extract the meaning behind it, ideally observing context FETCHING RESULTS FROM BACKEND SERVICES Provide information, insights and functionality from the input FORMULATE ANSWER Organize information in a coherent, readable format “We are sorry. There was a shortage on these shoes. You will receive them tomorrow” OUTPUT HOW AI CAN HELP WITH CHATBOTS THOUGH?
- 7. MACHINE LEARNING FOR NLP VR AND TEXT TO SPEECH POS TAGGING SENTIMENT ANALYSIS NATURAL LANGUAGE GENERATION MACHINE TRANSLATION DEPENDENCY PARSING ALREADY MANY ACHIEVEMENTS
- 8. TEXT NEEDS CONTEXT Cat Kitten Mat? Discrete atomic symbols THE PROBLEM WITH TEXT
- 9. EMBEDDINGS How words and sentences can be turned into numbers that machines can work with
- 10. BACKGROUND Recent but successful technique Unsupervisedly learned word embeddings have been exceptionally successful in many NLP tasks. Maybe the primary reason for NLP's breakout. Encoding general semantic relationships Beneficial to many downstream tasks Distributional hypothesis Words that are used and occur in the same contexts tend to purport similar meanings.
- 11. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 0 0 2 0 1 0Cat
- 12. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 2 0 1 0Cat Doc2 Doc5 Doc11 Doc13 Could be word counts in documents
- 13. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 1 0 1 0 cat cute drinks milk Bag of words, frequency count Bi-grams …. N-grams my cat is so cute when he drinks milk
- 14. EMBEDDINGS Vectors discussed so far are very high dimensional Techniques used to learn lower-dimensional vectors are called embeddings
- 15. LEARNING DENSE EMBEDDINGS Matrix factorization Glove, 2014 Shallow Neural Networks Word2Vec, 2013
- 16. MAIN ADVANTAGES ● One of the few currently successful applications of unsupervised learning. ● Can be derived from large sets of unannotated corpora ● Pre-trained embeddings can then be used in downstream tasks that use small amounts of labeled data.
- 17. WHAT CAN BE ACHIEVED?
- 19. SIMILARITY
- 20. SIMILARITIES
- 21. WORD ANALOGY
- 22. ANALOGIES
- 23. INTENT CLASSIFICATION Word embeddings are especially helpful when there is little training data I will travel to New York tomorrow I will leave for New York tomorrow I will take a flight to New York tomorrow {intent: travel}
- 24. ENTITY RECOGNITION Do you know a good vietnamese restaurant? {restaurant_types: [italian french, japanese]} {restaurant_type: vietnamese}
- 25. SOME REFERENCES Mikolov, T., Corrado, G., Chen, K., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. Proceedings of the International Conference on Learning Representations (ICLR 2013), 1–12. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality. NIPS, 1–9. Bootstrapping Dialog Systems with Word Embeddings https://www.cs.cmu.edu/~apparikh/nips2014ml-nlp/camera-ready/forgues_e tal_mlnlp2014.pdf https://www.npmjs.com/package/word2vec https://radimrehurek.com/gensim/
- 26. TELL US WHICH BOT YOU NEED, WE MOST PROBABLY KNOW HOW TO DO IT Web http://botfuel.io E-mail sales@botfuel.io Fueling the next generation of bots