+ Create new tricision Login 

Login



Forgot password?

First visit? Sign-up now!

By continuing you accept the Terms & Conditions and Privacy Policy.

time is up

Conversational AI Workshop - Question for Panelists

saved
Ideas
Pros and cons
 
Votes
Do you think that natural language generation or end-to-end conversational ai viable for production environments in the short term?
 
This question was discussed in 2017 Workshop panel
by Alborz
2
 
19

Alex, Michelle, Marion and 16 more

Given conversation is subjective, how can we evaluate the quality of Conversational AI?
by AR
10

JinYeong Bak, Michelle, Marion and 7 more

What are the main challenges to move from Q&A agents to conversational agents?
10

JinYeong Bak, Alex, Ehsan Hosseini-Asl and 7 more

How should we evaluate the quality of conversations?
8

Joseph, Kevin, Alex and 5 more

What are the major challenges and steps in bridging dialog systems in research and in production?
by Bing Liu
 
If the goal of research was to build something that really worked with natural dialog, then there... more
8

Michelle, Marion, Yuxi and 5 more

When the industrial and academic community will be able to create the ImageNet corpus for in domain and conversation dialogue system?
5

Greg, Cindy, Shreyas and 2 more

Killer apps? What is this stuff good for besides playing music and setting timers?
by Ken Church
3
Alex
Kenneth Church
Sebastian Blohm
Is it possible to have a conversational agent with also having a grounded understanding of language? In other words, if the agent participating in the conversation is not maintaining and evolving a world model, can it have a meaningful conversation?
2
Marion
MB
how do you think of the following statement about user simulators: "user behavior is more complicated than agent. If you can build a good user simulator for the RL algorithm to train, then you can might as well build a good agent simulator or agent policy using supervised learning. Then why shoul... more
3
Ivana Kruijff
TT
zwjyyc
How many of our current challenges will go away if we had 100x-1000x more data?
by Gerry Tesauro
2
Joe Bockhorst
Marion
When do you think we'll pass the Turing Test?
2
Ehsan Hosseini-Asl
Travis
What are some of the ethical and safety challenges you expect when productionizing data-driven dialog systems? Do you think these should be considered when doing purely research-based development?
2
JinYeong Bak
Marion
What is the best way to start dialogue modelling on a completely new domain/application? How would you structure this application if you knew from the outset that one needed this application delivered in multiple languages.
1
Marion
Please discuss the role of knowledge bases for conversational AI. Possible topics include: ontologies, ontology design, works well / doesn't work, what are most pressing open questions, how to leverage the KB in the conversation?
by Joe Bockhorst
1
Michael
How to deal with sensitive topics which a user might not want to say out loud? E.g., a user in a public place needing a doctor's appointment.
by Martin Tapp
1
JinYeong Bak
How do you regulate bias in conversational agents?
by Sanjana
 
Do you mean unfair social bias/prejudice? (or statistical bias?)
3
1
Verena Rieser
what are the challenges in using multi-modal datasets to build better dialogue agents ?
1
Michael
what do you think is the right way forward in designing better metrics for dialogue evaluation ?
1
Marion
Can the problem of conversational AI be re-formulated as a collaborative game between user and the bot given the success of Self-play RL similar to AlphaGo? End game situation is not one player winning but having a high conversation rating as a collaboration between two players.
1
Marion
Conversation involves two (or more) parties. How can we build a solo Conversational AI?
by AR
 
What do you mean by "solo Conversational AI"?
2
 
We tend to model conversational AI systems as individual agents. But conversation is a multi-agen... more
by AR
0
What would be the main characteristics you would seek for a GOOD, VALUABLE multi-party conversation data set?
by Peppo Valetto
 
What i mean is how to recognize an existing conversation data set in the wild that may be valuabl... more
by Peppo
0
Augmented Conversational AI
by Alex
How can we build systems where there's permanently a human in the loop to catch mistakes and edge... more
0
What is the current state of affairs with generating longer answers, with complex internal narrative and grounding in external knowledge graphs?
by Michael
0
Any good metrics of quality of longer (e.g., > 1 page) generated answers?
by Michael
0
What do you think about the ability to compose(composition) word sequences by RNN structures is impeded by the word embeddings or the architecture of RNN?
0
How important is it to go beyond differentiable loss functions when designing open domain chat bots ? What lies beyond cross-entropy and neg lot likelihood ?
0
How will I know how much your system knows about me? Is there a neat method of allowing the user to easily ask (or come to know) what information the system is using about them during the dialogue? How familiar and personalised are these systems going to become?
by Chris Watkins
0
(not related) Can you upload all the talks' videos?
0

Comments

http://www.tricider.com/brainstorming/2cifvidgPS7