“This is the 12th day of my participation in the Gwen Challenge in November. Check out the details: The Last Gwen Challenge in 2021.”

This paper introduces a tsinghua University open source online reverse dictionary Wanciwang

Site name: wantwords.thunlp.org/home/

Source code address: github.com/thunlp/Want…

What is a reverse dictionary? The meaning of a reverse dictionary is not a dictionary that provides antonyms, but a word that is the opposite of a regular (forward) dictionary that provides the definition of a query word and semantically matches the query description.

What does a reverse dictionary do?

The official website provides functions:

  • Solve the tip-of-the-tongue problem, the phenomenon of failing to retrieve a word from memory Take real life for example, for example, some usually very simple, very familiar words, words or formulas to the mouth is unable to remember, but suddenly remember after the exam.
  • Help New Language Learners
  • Help word selection (or word dictionary) anomia patients, People who can recognize and describe an object but fail to name it due to neurological disorder

In the NLP field, synonym substitution, text rewriting and text substitution are often used for data enhancement, and the open source dictionary is often the best corpus for data enhancement.

The dictionary supports independent queries in Chinese and English, and also supports chinese-English and English-Chinese conversion queries

Using the word as an example, you can see some interesting examples returned, some related to weibo comments and memes.

The official advice is to work with search filters to get better results.

Screening includes simple word count, stroke count and pinyin, as well as complex forms, rhymes and so on. This should also be useful for poetry generation and lyric generation.

We screen for words of four characters or more, and almost all of them come up with four-character idiomsJoy puts heart into a manandThe heaven and earth are astonishedPhrases like this

After the current experience, the queried words are quite interesting, which can be used as a corpus or knowledge base. If the subsequent API calls are open, they can be used for data enhancement, text matching, text generation and chattering robot. In addition, the english-Chinese/Chinese-English conversion effect is also very good.