How Tsinghua’s WantWords Reverse Dictionary Works and Why It Matters

What is a Reverse Dictionary?

A reverse dictionary takes a natural‑language description as input and returns a list of words whose meanings match that description. For example, the query “mountain is very high” yields candidates such as “高峻” and “巍峨”.

Typical Applications

Helps users overcome the tip‑of‑the‑tongue phenomenon (temporary word‑finding difficulty).

Assists language learners in expanding and consolidating vocabulary.

Supports aphasia patients who can describe an object but cannot recall its name.

Key Features

The system allows customization of part‑of‑speech tags and rhyme schemes, and supports four conversion modes: Chinese↔Chinese, Chinese↔English, English↔Chinese, and English↔English.

System Architecture

Core Model

The backbone is the Multi‑Channel Reverse Dictionary Model proposed by the THUNLP lab and published at AAAI‑2020. The model processes the input description through multiple semantic channels to generate candidate words.

Project Repository

GitHub: https://github.com/thunlp/WantWords

Code example

开源最前线（ID：
OpenSourceTop
） 猿妹 整编