Recent Advances in NLP
The document discusses recent advances in natural language processing (NLP). It begins with an introduction to the presenter and their background and credentials working in NLP, machine learning, and deep learning. It then provides a brief definition of NLP, describing it as programming computers to process large amounts of natural language at the intersection of computer science, artificial intelligence, and computational linguistics. The document goes on to provide several examples of recent NLP applications, technologies, and research topics, such as sentiment analysis, spell checking, machine translation, story generation from images and text, and using word embeddings and document vectors for visualization. It closes by acknowledging that while recent successes exist, general human-level NLP remains a significant challenge that will require
Recent Advances in NLP
- 1. Recent Advances in NLP Anuj Gupta Lead Data Scientist, FreshWorks @anujgupta82 anujgupta82@gmail.com
- 2. About Me I am a Lead Data Scientist at Freshworks; working in the areas of NLP, Machine Learning, Deep learning. Earlier he was heading ML efforts at Airwoot (now acquired by Freshworks) and Droom. Speaker at forums like Ainthill Indside, PyData, Fifth Elephant, ICDCN, PODC, IIT Delhi, IIIT Hyderabad and special interest groups like DLBLR. @anujgupta82 anujgupta82@gmail.com
- 3. What is NLP • Concerned with programming computers to fruitfully process large natural language. • It is at the intersection of computer science, artificial intelligence and computational linguistics
- 4. Analogies
- 5. Demo
- 9. Resurrect your dead friend as an AI Luka - Eugenia lost her friend Roman in an accident. Determined not to lose his memory, she gathered all the texts Roman sent over his short life and made a chatbot – a program that responds automatically to text messages. Now whenever she is missing Roman, Eugenia sends the chatbot a message and Roman’s words respond.
- 11. Spell checking
- 12. Retail Search
- 13. • Co-reference (e.g. What does "he" or "it" refer to given a document?)
- 14. • Machine Translation (e.g. translate Chinese text to English)
- 15. http://www.spndev.com/neww2v.html Word2Vec model on Fox News broadcasts
- 16. Artworks mapped using Machine Learning. Art work Mapped using t-SNE https://artsexperiments.withgoogle.com/tsnemap/#47.68,1025.98,361.43,51.29,0.00,271.67
- 18. Story generation from images
- 19. Story generation from images
- 21. Document Vectors Visualization of wikipedia paragraph vectors
- 24. ● Shakespeare’s work ● Linux Source Code
- 25. ● Algebraic Geometry ● NSF Research Awards abstracts
- 28. “Toward Controlled Generation of Text” - Zhiting Hu et.al 2017
- 29. Dr QA
- 30. NLP is not easy !
- 31. NLP is not easy !
- 32. • The examples we have seen are cherry picked success stories. • We are still far from building general AI to understand NLP – there are a lot of fundamental pieces that need to be solved as a precursor. • None the less in last 5 yrs lot of exiting work that has happened. • A key quest has been building systems/models that are not black box. • There are no shortcuts.