WARNING. This post contains references to self-harm and suicide. It includes conversations between a human and DialoGPT, with the sole purpose of surfacing the danger of uncontrolled AI. If you or a loved one are dealing or have dealt with suicidal thoughts, I suggest skipping this article.In the context of an accelerating mental health crisis, Natural Language … [Read more...] about Unconstrained Chatbots Condone Self-Harm
Conversational AI
Amazon Releases 51-Language Dataset for Language Understanding
Imagine that all people around the world could use voice AI systems such as Alexa in their native tongues.One promising approach to realizing this vision is massively multilingual natural-language understanding (MMNLU), a paradigm in which a single machine learning model can parse and understand inputs from many typologically diverse languages. By learning a shared data … [Read more...] about Amazon Releases 51-Language Dataset for Language Understanding
How To Structure Intent In Chatbots And Gather Useful Feedback
I recently collaborated on several projects involving chatbots and had the opportunity to discuss with industry experts about the main difficulties that are often encountered in this type of project. While it is becoming easier and easier to build conversational assistants, it looks like there are some problems that emerge systematically as the chatbot grows, as a consequence … [Read more...] about How To Structure Intent In Chatbots And Gather Useful Feedback
State-of-the-art Approaches to Building Open-Domain Conversational Agents
This research summary is part of our Conversational AI series which covers the latest AI & machine learning approaches in the following areas:Open-domain chatbotsTask-oriented chatbotsDialog datasetsEvaluation metricsIn this piece, we start by covering the cutting-edge approaches to building open-domain dialog agents.2020 is the breakthrough year for open-domain … [Read more...] about State-of-the-art Approaches to Building Open-Domain Conversational Agents
Key Research Advances in Building Task-Oriented Dialog Agents
This research summary is part of our Conversational AI series which covers the latest AI & machine learning approaches in the following areas:Open-domain chatbotsTask-oriented chatbotsDialog datasetsEvaluation metricsIn this research summary, we feature some of the most interesting novel approaches to improving the performance of task-oriented, or goal-oriented, … [Read more...] about Key Research Advances in Building Task-Oriented Dialog Agents
Novel Datasets For Open-Domain & Task-Oriented Dialogs
This research summary is part of our Conversational AI series which covers the latest AI & machine learning approaches in the following areas:Open-domain chatbotsTask-oriented chatbotsDialog datasetsEvaluation metricsIn this post, we review the recently introduced datasets for training, validating, and evaluating dialog systems.Recent progress in language … [Read more...] about Novel Datasets For Open-Domain & Task-Oriented Dialogs
New Ways to Evaluate Open-Domain Conversational Agents
This research summary is part of our Conversational AI series which covers the latest AI & machine learning approaches in the following areas:Open-domain chatbotsTask-oriented chatbotsDialog datasetsEvaluation metricsIn this last part of the series, we discuss the latest approaches to evaluation of dialog agents.Evaluating open-domain dialog agents remains a … [Read more...] about New Ways to Evaluate Open-Domain Conversational Agents
NeurIPS 2020: Key Research Papers in Natural Language Processing (NLP) & Conversational AI
NeurIPS is the largest machine learning conference held every December. It brings together researchers in computational neuroscience, reinforcement learning, deep learning, and their applications such as computer vision, fairness and transparency, natural language processing, robotics, and more.Our team reviewed the papers accepted to NeurIPS 2020 and shortlisted the most … [Read more...] about NeurIPS 2020: Key Research Papers in Natural Language Processing (NLP) & Conversational AI
Evaluation Metrics For Dialog Systems
Evaluation is a crucial part of the dialog system development process. Human judgment is considered a gold standard for the evaluation of dialog agents. However, this is also a very expensive and time-intensive approach. Thus, researchers mostly rely on automatic metrics when developing dialog systems.In this article, we’ll introduce a brief overview of the key evaluation … [Read more...] about Evaluation Metrics For Dialog Systems
Key Dialog Datasets: Overview and Critique
To build a state-of-the-art dialog system, you need challenging tasks for model training and evaluation. There are numerous dialog datasets that assist researchers in building task-oriented and chit-chat dialog agents. In particular, the Facebook Research team has introduced a framework, called ParlAI (pronounced par-lay), where they’ve gathered together 80+ popular dialog … [Read more...] about Key Dialog Datasets: Overview and Critique