Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation

TL;DR

This paper introduces an interactive text ranking method using Bayesian optimisation to efficiently select high-quality candidates in community QA and summarisation, outperforming existing approaches and enhancing reinforcement learning rewards.

Contribution

It presents a novel Bayesian optimisation-based interactive ranking approach that effectively handles small data and integrates prior knowledge for NLP tasks.

Findings

Significantly outperforms existing interactive methods in community QA and summarisation.

The learned ranking function serves as an effective reward for reinforcement learning.

Improves state-of-the-art in interactive summarisation.

Abstract

For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs. To address the lack of user-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method employs Bayesian optimisation to focus the user's labelling effort on high quality candidates and integrates prior knowledge in a Bayesian manner to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive summarisation, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarisation.