EMNLP 2023long main0 citations
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
Wang Zhu, Jesse Thomason, Robin Jia
Abstract
We propose Chain-of-Questions, a framework that trains a model to robustly answer multistep questions by generating and answering sub-questions. We obtain supervision for sub-questions from human-annotated question decomposition meaning representation (QDMR), but QDMR does not include annotated answers to sub-questions. To overcome this technical challenge, we treat sub-answers as latent variables and infer them with a novel dynamic mixture of Hard-EM and MAPO. Chain-of-Questions is effective and robust, greatly outperforming strong neuro-symbolic methods by 9.0 F1 on a DROP contrast set and GPT-3.5 by 24.3 F1 on a HotpotQA adversarial set.
multistep reasoningquestion answeringlatent variable learning
BibTeX
@inproceedings{
zhu2023chainofquestions,
title={Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering},
author={Wang Zhu and Jesse Thomason and Robin Jia},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=SfI8GT3xdb}
}