Science & Technology

Channels: Science & Technology | Financial Markets | Artificial Intelligence | Blockchain


Rasa's conversational AI can selectively ignore bits of dialogue to improve its responses

[2019.10.09, Wed 16:05] What might be the key to chatbots or voice-enabled assistants that respond in more natural, human-like ways? Researchers at Rasa, a Berlin, Germany-based startup developing a standard infrastructure layer for conversational AI, believe selective attention might play an outsized role. In a preprint paper published this week on Arxiv.org, they detail a system that can selectively ignore or attend to dialogue history, enabling it to skip over responses in turns of dialogue that don't directly address the previous utterance. The team proposes what they call the Transformer Embedding Dialogue policy, which chooses which diaogue turns to skip with the help of transformers. Importantly, the researchers say that the TED policy - which can be used in either a modular or end-to-end fashion - doesn't assume any given whole dialogue sequence is relevant for choosing an answer to an utterance. Although the data set wasn't ideal for supervised learning of dialogue policies, due in part to its lack of historical dependence, the researchers report that the model successfully recovered from "Non-cooperative" user behavior and outperformed baseline approaches at every dialogue turn. Rasa hasn't yet incorporated the model into production systems, but it could bolster its suite of conversational AI tools - Rasa Stack - targeting verticals like sales and marketing and advanced customer service in health care, insurance, telecom, banking, and other enterprise verticals. Adobe recently used Rasa's tools to build an AI assistant that enables users to search through Adobe Stock using natural language commands.
Read on VentureBeat.com >   Google the news >>

<< Back


(c) 2019 Geo Glance