Multitasking Framework for Unsupervised Simple Definition Generation

TL;DR

This paper introduces SimpDefiner, a multitasking framework that generates simple definitions for words without requiring learner's dictionaries, aiding language learners and low literacy readers by leveraging standard dictionaries and corpora.

Contribution

The paper presents a novel multitasking approach for simple definition generation that works with standard dictionaries and corpora, eliminating the need for specialized learner's dictionaries.

Findings

Outperforms baseline with a 1.77 SARI score improvement on English data.

Increases low-level (HSK 1-3) word proportion in Chinese definitions by 3.87%.

Generates relevant, simple definitions validated by automatic and manual evaluations.

Abstract

The definition generation task can help language learners by providing explanations for unfamiliar words. This task has attracted much attention in recent years. We propose a novel task of Simple Definition Generation (SDG) to help language learners and low literacy readers. A significant challenge of this task is the lack of learner's dictionaries in many languages, and therefore the lack of data for supervised training. We explore this task and propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts. We disentangle the complexity factors from the text by carefully designing a parameter sharing scheme between two decoders. By jointly training these components, the framework can generate both complex and simple definitions simultaneously. We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets. Our method outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87%.