Multi-Channel Reverse Dictionary Model

Authors

  • Lei Zhang Tsinghua University
  • Fanchao Qi Tsinghua University
  • Zhiyuan Liu Tsinghua University
  • Yasheng Wang Huawei Noah's Ark Lab
  • Qun Liu Huawei Noah's Ark Lab
  • Maosong Sun Tsinghua University

DOI:

https://doi.org/10.1609/aaai.v34i01.5365

Abstract

A reverse dictionary takes the description of a target word as input and outputs the target word together with other words that match the description. Existing reverse dictionary methods cannot deal with highly variable input queries and low-frequency target words successfully. Inspired by the description-to-word inference process of humans, we propose the multi-channel reverse dictionary model, which can mitigate the two problems simultaneously. Our model comprises a sentence encoder and multiple predictors. The predictors are expected to identify different characteristics of the target word from the input query. We evaluate our model on English and Chinese datasets including both dictionary definitions and human-written descriptions. Experimental results show that our model achieves the state-of-the-art performance, and even outperforms the most popular commercial reverse dictionary system on the human-written description dataset. We also conduct quantitative analyses and a case study to demonstrate the effectiveness and robustness of our model. All the code and data of this work can be obtained on https://github.com/thunlp/MultiRD.

Downloads

Published

2020-04-03

How to Cite

Zhang, L., Qi, F., Liu, Z., Wang, Y., Liu, Q., & Sun, M. (2020). Multi-Channel Reverse Dictionary Model. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01), 312-319. https://doi.org/10.1609/aaai.v34i01.5365

Issue

Section

AAAI Technical Track: AI and the Web