Preference-based Interactive Multi-Document Summarisation

06/07/2019
by   Yang Gao, et al.
0

Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applied, but the existing methods require several thousand interaction rounds even in simulations with perfect user feedback. In this paper, we study preference-based interactive summarisation. To reduce the number of interaction rounds, we propose the Active Preference-based ReInforcement Learning (APRIL) framework. APRIL uses Active Learning to query the user, Preference Learning to learn a summary ranking function from the preferences, and neural Reinforcement Learning to efficiently search for the (near-)optimal summary. Our results show that users can easily provide reliable preferences over summaries and that APRIL outperforms the state-of-the-art preference-based interactive method in both simulation and real-user experiments.

READ FULL TEXT
research
08/29/2018

APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning

We propose a method to perform automatic document summarisation without ...
research
07/11/2023

Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores

Interactive reinforcement learning has shown promise in learning complex...
research
09/10/2023

Learning Personalized User Preference from Cold Start in Multi-turn Conversations

This paper presents a novel teachable conversation interaction system th...
research
12/06/2016

Coactive Critiquing: Elicitation of Preferences and Features

When faced with complex choices, users refine their own preference crite...
research
12/02/2021

Personal Comfort Estimation in Partial Observable Environment using Reinforcement Learning

The technology used in smart homes have improved to learn the user prefe...
research
12/01/2018

Explore-Exploit: A Framework for Interactive and Online Learning

Interactive user interfaces need to continuously evolve based on the int...
research
11/14/2022

Interactively Learning to Summarise Timelines by Reinforcement Learning

Timeline summarisation (TLS) aims to create a time-ordered summary list ...

Please sign up or login with your details

Forgot password? Click here to reset