Opposite to a regular (forward) dictionary that provides definitions for query words, a reverse dictionary returns words semantically matching the query descriptions.
The core model of WantWords is based on our proposed Multi-channel Reverse Dictionary Model [paper] [code], as illustrate in the following figure.
If the code or data help you, please cite the following two papers.
@inproceedings{qi2020wantwords,
title={WantWords: An Open-source Online Reverse Dictionary System},
author={Qi, Fanchao and Zhang, Lei and Yang, Yanhui and Liu, Zhiyuan and Sun, Maosong},
booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
pages={175--181},
year={2020}
}
@inproceedings{zhang2020multi,
title={Multi-channel reverse dictionary model},
author={Zhang, Lei and Qi, Fanchao and Liu, Zhiyuan and Wang, Yasheng and Liu, Qun and Sun, Maosong},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
pages={312--319},
year={2020}
}