User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant

by   Nicolas Lair, et al.

People are becoming increasingly comfortable using Digital Assistants (DAs) to interact with services or connected objects. However, for non-programming users, the available possibilities for customizing their DA are limited and do not include the possibility of teaching the assistant new tasks. To make the most of the potential of DAs, users should be able to customize assistants by instructing them through Natural Language (NL). To provide such functionalities, NL interpretation in traditional assistants should be improved: (1) The intent identification system should be able to recognize new forms of known intents, and to acquire new intents as they are expressed by the user. (2) In order to be adaptive to novel intents, the Natural Language Understanding module should be sample efficient, and should not rely on a pretrained model. Rather, the system should continuously collect the training data as it learns new intents from the user. In this work, we propose AidMe (Adaptive Intent Detection in Multi-Domain Environments), a user-in-the-loop adaptive intent detection framework that allows the assistant to adapt to its user by learning his intents as their interaction progresses. AidMe builds its repertoire of intents and collects data to train a model of semantic similarity evaluation that can discriminate between the learned intents and autonomously discover new forms of known intents. AidMe addresses two major issues - intent learning and user adaptation - for instructable digital assistants. We demonstrate the capabilities of AidMe as a standalone system by comparing it with a one-shot learning system and a pretrained NLU module through simulations of interactions with a user. We also show how AidMe can smoothly integrate to an existing instructable digital assistant.


Benchmarking Natural Language Understanding Services for building Conversational Agents

We have recently seen the emergence of several publicly available Natura...

Intent Features for Rich Natural Language Understanding

Complex natural language understanding modules in dialog systems have a ...

Towards Open Intent Detection

The open intent detection problem is presented in this paper, which aims...

The Intuitive Power of Graph Pivots For User Exploration and Adaptive Data Abstraction

This paper reports on a simple visual technique that boils extracting a ...

A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery

Intent Detection is one of the tasks of the Natural Language Understandi...

Prompt Learning for Domain Adaptation in Task-Oriented Dialogue

Conversation designers continue to face significant obstacles when creat...

Natural Language Sentence Generation from API Specifications

APIs are everywhere; they provide access to automation solutions that co...

Please sign up or login with your details

Forgot password? Click here to reset