Reverse dictionary

Abstract: Distributional models that learn rich semantic word representations are a success story of recent NLP research. However, developing models that learn useful representations of phrases and sentences has proved far harder. We propose using the definitions found in everyday dictionaries as a means of bridging this gap between lexical and phrasal semantics. Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions. We present two applications of these architectures: 'reverse dictionaries' that return the name of a concept given a definition or description and general-knowledge crossword question answerers. On both tasks, neural language embedding models trained on definitions from a handful of freely-available lexical resources perform as well or better than existing commercial systems that rely on significant task-specific engineering. The results highlight the effectiveness of both neural embedding architectures and definition-based training for developing models that understand phrases and sentences.

Abstract: The identity of a word entered on DTMF (Dual Tone Multi-Frequency) pushbuttons is determined by identifying letters according to their frequency in groups of 2s and 3s and up to n-letter groups. Initially, a sender will type a word on a DTMF pushbutton pad. Since each button represents three (3) possible letters, or four in the case of 7 (PQRS) and 9 (WXYZ), the system will look up the possible meanings for the word from an internal memory which includes a dictionary. If the word does not exist in the dictionary, then the system will search against a Forward and a Reverse Dictionary to guess at the identity of fragments from the beginning and ending of the word. Then it will guess the identity of each letter according to its relative frequency in groups of 3s known as Trigrams, or in groups of 2s known as Digrams. The Trigams are preferably arranged in five (5) files to identify the first, second, third and final letters of a word as well as any non-specified middle location. The system can be extended to any letter grouping of size n where n is two or more. Once identified, the word is stored as part of a message and then transmitted as ASCII digital information over a packet data network to a remote receiver where digital to voice synthesis converts the message into audio. Other delivery methods include alphanumeric pagers, FAX, E-Mail, telex, computer printed output, telegrams and cables.

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.

Abstract: Meaning conflation deficiency is one of the main limiting factors of word representations which, given their widespread use at the core of many NLP systems, can lead to inaccurate semantic understanding of the input text and inevitably hamper the performance. Sense representations target this problem. However, their potential impact has rarely been investigated in downstream NLP applications. Through a set of experiments on a state-of-the-art reverse dictionary system based on neural networks, we show that a simple adjustment aimed at addressing the meaning conflation deficiency can lead to substantial improvements.