Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation
arXiv:1911.10183
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.
Accepted to Transactions of the ACL
References in corpus (6)
- Practical Bayesian Optimization of Machine Learning Algorithms
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Bayesian Active Learning for Classification and Preference Learning
- Active Learning for Visual Question Answering: An Empirical Study
- Passage Ranking with Weak Supervision
- Bayesian active learning for choice models with deep Gaussian processes