Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling
This work addresses the problem of inefficient modeling and dataset creation in definition modeling for natural language applications, though it is incremental as it builds on existing SDM tasks.
The paper tackles the limitations of Single Definition Modeling (SDM) by introducing Multiple Definition Modeling (MDM), which pools contexts and definitions to exploit correlations, resulting in improved SDM performance through pretraining and comparable zero-shot results.
Definition modeling is an important task in advanced natural language applications such as understanding and conversation. Since its introduction, it focus on generating one definition for a target word or phrase in a given context, which we refer to as Single Definition Modeling (SDM). However, this approach does not adequately model the correlations and patterns among different contexts and definitions of words. In addition, the creation of a training dataset for SDM requires significant human expertise and effort. In this paper, we carefully design a new task called Multiple Definition Modeling (MDM) that pool together all contexts and definition of target words. We demonstrate the ease of creating a model as well as multiple training sets automatically. % In the experiments, we demonstrate and analyze the benefits of MDM, including improving SDM's performance by using MDM as the pretraining task and its comparable performance in the zero-shot setting.