Goto

Collaborating Authors

How to build smarter chatbots

#artificialintelligence

We're going to be blunt: Chatbots in their current form aren't great. We were promised bots that would change the way we interact with businesses and services, but instead we have interactive bots that perform worse than apps. They are primarily focused on taps or interactive graphical interfaces, and conversing with them using natural language is nearly impossible. Take an example of Poncho Weather on Facebook Messenger. Let's say I'm going to a conference next Monday in San Diego and want to know what the forecast is.


How to build smarter chatbots

#artificialintelligence

We're going to be blunt: Chatbots in their current form aren't great. We were promised bots that would change the way we interact with businesses and services, but instead we have interactive bots that perform worse than apps. They are primarily focused on taps or interactive graphical interfaces, and conversing with them using natural language is nearly impossible. Take an example of Poncho Weather on Facebook Messenger. Let's say I'm going to a conference next Monday in San Diego and want to know what the forecast is.


A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents

arXiv.org Artificial Intelligence

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given that the amount of dialogue history and corresponding representations can play an important role in the overall performance of a conversational system. This paper studies the amount of history required by conversational agents for reliably predicting dialogue rewards. The task of dialogue reward prediction is chosen for investigating the effects of varying amounts of dialogue history and their impact on system performance. Experimental results using a dataset of 18K human-human dialogues report that lengthy dialogue histories of at least 10 sentences are preferred (25 sentences being the best in our experiments) over short ones, and that lengthy histories are useful for training dialogue reward predictors with strong positive correlations between target dialogue rewards and predicted ones.


Chatbots with Machine Learning: Building Neural Conversational Agents

#artificialintelligence

Have you ever talked to Siri, Alexa, or Cortana to set up an alarm, call friends, or arrange a meeting? Many people may agree that despite their usefulness in common and routine tasks, it's difficult to force conversational agents to talk on general, sometimes philosophical topics. The Statsbot team invited a data scientist, Dmitry Persiyanov, to explain how to fix this issue with neural conversational models and build chatbots using machine learning. Interacting with the machine via natural language is one of the requirements for general artificial intelligence. This field of AI is called dialogue systems, spoken dialogue systems, or chatbots.


Top Research Papers in Conversational AI For Chatbots And Intelligent Agents

#artificialintelligence

Conversational interfaces are permeating all aspects of our digital experiences. Digital assistants work alongside human agents to provide customer support. Chatbots are used to both market products and enable their purchases. IoT and other smart devices like Google Home or Amazon Echo enable hands-free operation through voice commands. Businesses are also starting to replace clunky enterprise UI for streamlined natural language interfaces to improve productivity and output.