A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection

05/04/2022
by   Ankan Mullick, et al.
0

Systems like Voice-command based conversational agents are characterized by a pre-defined set of skills or intents to perform user specified tasks. In the course of time, newer intents may emerge requiring retraining. However, the newer intents may not be explicitly announced and need to be inferred dynamically. Thus, there are two important tasks at hand (a). identifying emerging new intents, (b). annotating data of the new intents so that the underlying classifier can be retrained efficiently. The tasks become specially challenging when a large number of new intents emerge simultaneously and there is a limited budget of manual annotation. In this paper, we propose MNID (Multiple Novel Intent Detection) which is a cluster based framework to detect multiple novel intents with budgeted human annotation cost. Empirical results on various benchmark datasets (of different sizes) demonstrate that MNID, by intelligently using the budget for annotation, outperforms the baseline methods in terms of accuracy and F1-score.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/22/2020

Intent Mining from past conversations for Conversational Agent

Conversational systems are of primary interest in the AI community. Chat...
research
07/27/2021

Energy-based Unknown Intent Detection with Data Manipulation

Unknown intent detection aims to identify the out-of-distribution (OOD) ...
research
04/12/2022

Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset

Dialog systems must be capable of incorporating new skills via updates o...
research
04/27/2020

Spatial-Temporal Mitosis Detection in Phase-Contrast Microscopy via Likelihood Map Estimation by 3DCNN

Automated mitotic detection in time-lapse phasecontrast microscopy provi...
research
03/16/2021

Automatic Intent-Slot Induction for Dialogue Systems

Automatically and accurately identifying user intents and filling the as...
research
09/21/2018

Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection

In an effort to assist factcheckers in the process of factchecking, we t...

Please sign up or login with your details

Forgot password? Click here to reset