Dialogue policies play a crucial role in developing task-oriented dialogue systems, yet their development and maintenance are challenging and typically require substantial effort from experts in dialogue modeling. While in many situations, large amounts of conversational data are available for the task at hand, people lack an effective solution able to extract dialogue policies from this data. In this paper, we address this gap by first illustrating how Large Language Models (LLMs) can be instrumental in extracting dialogue policies from datasets, through the conversion of conversations into a unified intermediate representation consisting of canonical forms. We then propose a novel method for generating dialogue policies utilizing a controllable and interpretable graph-based methodology. By combining canonical forms across conversations into a flow network, we find that running graph traversal algorithms helps in extracting dialogue flows. These flows are a better representation of the underlying interactions than flows extracted by prompting LLMs. Our technique focuses on giving conversation designers greater control, offering a productivity tool to improve the process of developing dialogue policies.

Privacy policies play a vital role in safeguarding user privacy as legal jurisdictions worldwide emphasize the need for transparent data processing. While the suitability of privacy policies to enhance transparency has been critically discussed, employing conversational AI systems presents unique challenges in informing users effectively. In this position paper, we propose a dynamic workflow for transforming privacy policies into privacy question-and-answer (Q&A) pairs to make privacy policies easily accessible through conversational AI. Thereby, we facilitate interdisciplinary collaboration among legal experts and conversation designers, while also considering the utilization of large language models' generative capabilities and addressing associated challenges. Our proposed workflow underscores continuous improvement and monitoring throughout the construction of privacy Q&As, advocating for comprehensive review and refinement through an experts-in-the-loop approach.

Clap along, if you feel like that's what you wanna do Back in 2014, hip-hop producer Pharrell Williams wrote Happy for his friend Cee Lo Green, and had him record the song to include on Pharrell's upcoming album. Unfortunately, Cee Lo Green's record label executives vetoed the song's release, believing it would subtract attention from Green's own upcoming album. Upset but unfazed by this idiotic slight toward him, Pharrell recorded a new version of the song himself, and simply released that instead. "Happy" went on to become one of the singular most popular recorded songs in history, breaking every record one single song can break along the way and sending Pharrell's career to new and rarified heights. We are pleased to announce the Women Leaders of Conversational AI, Class of 2023: approximately 200 women who themselves have shown perseverance in their own careers as they've worked to impact the conversational AI / voice technology continuum.

Portfolios are always a hot topic in career Q&As and the conversation design community, and for good reason! A portfolio is a great way to highlight your writing and design skills, but with a little creativity, they can speak to so much more than just a prototype. I put together my top considerations and must-have skills for your own portfolio, to ensure that it speaks for you, and that your ideal audience will understand your work and what you're most passionate about when it comes to conversation design. Later in this post, Brielle Nickoloff and I review four portfolios from real conversation designers! This is the most obvious and most important thing to highlight in your portfolio.

Have you ever wondered who designs a chatbot conversation? Who decides what reply the bot will give? How does the chatbot respond? I stumbled upon an opportunity to write conversations for chatbots without any prior technical knowledge. All you need is to be creative with your words and create conversations that are human-centric.

Have you ever wondered how chatbots can understand natural language and answer using the same linguistic code? The answer is simple: behind every chatbot there's a human being or a team of human beings (often) called Conversation Designers, who give them a human voice. The bases of any frictionless interaction are the ability to understand unambiguously and the ability to answer accordingly. Human-Chatbot communication makes no exception. A chatbot understands messages thanks to NLP technologies that analyze and interpret natural languages using complex Machine Learning algorithms. Conversation Designers (working as Computational Linguists) train these algorithms, feeding them with pre-analyzed set of texts that work as the examples that the machine uses to "learn".

Developing a brand used to mean creating a logo and choosing color palettes, but those days are numbered. Thanks to chatbots and intelligent hardware devices such as Amazon Alexa and Google Home, visual brand elements are starting to take a backseat to brand elements that are completely focused on what people will read or hear. Companies building products on chatbot platforms aren't always able to control the appearance of what they're communicating to their users -- it's all about the words. This applies to an even greater extent with smart speakers because the words are spoken and you have nothing to show to your users. Product designers who are focused on these platforms are going to have to learn how to shift from a visual mindset to a world where picking the right words and communication style is what will help them to stand out from the competition.