WantWords: An Open-source Online Reverse Dictionary System

Abstract

A reverse dictionary takes descriptions of words as input and outputs words semantically matching the input descriptions. Reverse dictionaries have great practical value such as solving the tip-of-the-tongue problem and helping new language learners. There have been some online reverse dictionary systems, but they support English reverse dictionary queries only and their performance is far from perfect. In this paper, we present a new open-source online reverse dictionary system named WantWords (https://wantwords. thunlp.org/). It not only significantly outperforms other reverse dictionary systems on English reverse dictionary performance, but also supports Chinese and English-Chinese as well as Chinese-English cross-lingual reverse dictionary queries for the first time. Moreover, it has user-friendly front-end design which can help users find the words they need quickly and easily. All the code and data are available at https://github.com/ thunlp/WantWords.

IRB-NLP at SemEval-2022 Task 1: Exploring the Relationship Between Words and Their Semantic Representations

“…Finally, the ranks of our team are given (and the number of teams competing in a subtask). (9) 1 (9) 1 (9) 3 (7) 2 (7) 2 (7) 3 (6) 1 (6) 1 (6) 3 (7) 1 (7) 1 (7) 4 (6) 2 (6) 1 ( 7) 7 ( 7) 1 (7) 3 ( 5) 5 ( 5) 1 (5) 3 ( 5) 4 ( 5) 2 ( 5) 5 ( 6) 5 ( 6) 1 (6) 3 ( 5) 4 ( 5 (Bevilacqua et al, 2020;Gadetsky et al, 2018;Mickus et al, 2019;Noraset et al, 2017;Yang et al, 2020;Zhu et al, 2019). Additionally, these approaches make use of the pre-trained word embeddings that carry the semantic information extracted from a huge corpus.…”

“…Subsequent work on Definition Modeling focused on variations of the problem of prediction of a word gloss from the word sense. These approaches consider gloss prediction based on sensespecific word embeddings (Gadetsky et al, 2018;Kabiri and Cook, 2020;Zhu et al, 2019), and on a word-based context indicating the word sense (Bevilacqua et al, 2020;Gadetsky et al, 2018;Mickus et al, 2019;Yang et al, 2020;. The proposed approaches are based either on RNNs (Gadetsky et al, 2018;Kabiri and Cook, 2020;Zhu et al, 2019) or Transformers (Bevilacqua et al, 2020;Mickus et al, 2019).…”

“…The variation can be great even for the same language and experimental setup (Kabiri and Cook, 2020). The original approach of Noraset et al (2017) remains competitive in the sense-aware setting, with the sense-aware approaches achieving BLEU increases that range between 1 − 2 (Gadetsky et al, 2018;Kabiri and Cook, 2020; and 5 − 6 (Kabiri and Cook, 2020;Yang et al, 2020;, depending on the setting.…”

“…Recent REVDICT approaches utilize deep learning (DL) to map arbitrary-length definition phrases to the vector representation of the target word (Hill et al, 2016;Malekzadeh et al, 2021;Qi et al, 2020;Yan et al, 2020). The success of DL approaches indicates that REVDICT can be solved implicitly, i.e.…”

Semeval-2022 Task 1: CODWOE -- Comparing Dictionaries and Word Embeddings

“…Since then, a number of works have attempted to implement reverse dictionaries using neural language models. The WantWords system (Zhang et al, 2020b;Qi et al, 2020) is based on a BiLSTM architecture, and incorporates auxiliary tasks such as part-of-speech prediction to boost the performance. Yan et al (2020) seeks to replace the learned neural language models in Hill et al (2016) or WantWords with a pre-trained model such as BERT (Devlin et al, 2019) and its multilingual variants, which allows them to use their system in a cross-lingual setting-querying in a language to obtain an answer in another.…”