Neural Networks

Sharing Words

DAN 402

DAN 416

Title: Conditional Text Generation and Pretraining
Rush will discuss recent efforts to build robust text generation systems for problems like summarization and data-to-text generation and the challenges compared to highly constrained tasks such as machine translation. The focus of this talk will be on pretraining and whether it has the potential to change the landscape of this area. Rush will discuss early experiments showing its usefulness, but argue that high-precision conditional text generation still remains a difficult task.

Convolutional Neural Networks

Recurrent Neural Networks

DAN 402

DAN 416

Title: Evaluating Conversational Agents

There has been a renewed focus on dialog systems, including non-task driven conversational agents. Dialog is a challenging problem since it spans multiple conversational turns. To further complicate the problem, there are many possible valid utterances which may be semantically different. This makes automatic evaluation difficult, which is why the current best practice for analyzing and comparing dialog systems is the use of human judgments. This talk focuses on evaluation, presenting a theoretical framework for the systematic evaluation of open-domain conversational agents, including the usage of Item Response Theory (Lord, 1968) for efficient chatbot evaluation and evaluation set creation. We introduce ChatEval (https://chateval.org) a unified framework for human evaluation of chatbots that augments existing tools and provides a web-based hub for researchers to share and compare their dialog systems.

Attention: A Quick Recap

Transformers

Contextualized embeddings: ELMo, GPT, BERT

DAN 402

DAN 416

Title: Grounding Language in Pixels: Recent Work on Neural Vision and Language Understanding

Saenko will talk about recent work on joint vision and language understanding using neural networks. The talk will cover a range of problems including referring expression grounding, visual question answering, text-to-image and text-to-video retrieval, image and video captioning, and language-based navigation. Saenko will discuss issues of feature representation, relational reasoning and explainability of the resulting models.

Memory-based models. External knowledge integration

Deep Question Answering

DAN 402

DAN 416

Multi-skill conversational agents

Hierarchy in neural dialogue models

Dialogue diversity

DAN 402

DAN 416

Title: Putting together the threads of conversational AI?

Maybe we don't have enough threads yet to knit together the whole, but let's try anyway! We present our view of what is necessary for conversational AI, and the pieces we have worked on so far to get there. In particular: software (ParlAI, a unified platform for dialogue research), various neural architectures for memory, reasoning, retrieval and generation, and interactive learning, tasks for employing personality (PersonaChat), knowledge (Wizard of Wikipedia) and perception (Image-Chat), evaluation studies & techniques (dialogue NLI), and a recent competition (ConvAI2) we ran that shows unfortunately how far we still have to go.