CS 224V

Conversational Virtual Assistants with Deep Learning

Fall 2022

About CS 224V

Computers will transform into effective, personalized, conversational assistants for everybody, including the pre-literate and the non-literate. Commercial chatbots today are notoriously brittle as they are hardcoded to handle a few possible choices of user inputs. Recently introduced large language neural models, such as GPT-3, are remarkably fluent, but they are often erroneous and prone to hallucinations. This course studies how we can tame these neural models into robust, trustworthy, and cost-effective conversational agents across all industries and languages.

Students will learn both the theory and practice with two assignments, and a major open-ended course project of their own design.

Topics include:

  • Formal, executable meaning representation for conversational virtual assistants
  • Contextual neural semantic parser for translating dialogues into a formal representation.
  • Automatic generation of training data for dialogues from high-level schema and API specification with large language models.
  • Using large language models in virtual assistants.
  • Multilingual, mixed-initiative, multimodal assistants.
  • Federated privacy-protecting assistants.


👩‍🏫 Instructor Monica Lam
(lam at cs)
👩 CA Jian Vora
(jianv at cs)
👩 CA Paridhi Maheshwari
(paridhi at cs)
🕒 Time Mon, Wed 3:00-4:20pm
🏫 Location Turing Auditorium
💳 Credits 3-4 units

Office Hours

MonicaWed 4:20pm, Turing Aud
ParidhiTue 11am-12pm, 240-202
JianMon 4:20pm, Turing Aud


Prerequisites: one of LINGUIST 180/280, CS 124, CS 224N, CS 224S, 224U.


Grading is according to the following scheme: