CASE: Context-Aware Semantic Expansion
This work addresses a problem in natural language processing for applications like query suggestion and computer-assisted writing, but it is incremental as it builds on similar tasks and focuses on automated annotation.
The paper tackles the task of Context-Aware Semantic Expansion (CASE), which suggests alternative terms fitting a sentential context for a seed term, and demonstrates that annotations for this task can be automatically harvested from existing corpora, achieving competitive results on a dataset of 1.8 million sentences.
In this paper, we define and study a new task called Context-Aware Semantic Expansion (CASE). Given a seed term in a sentential context, we aim to suggest other terms that well fit the context as the seed. CASE has many interesting applications such as query suggestion, computer-assisted writing, and word sense disambiguation, to name a few. Previous explorations, if any, only involve some similar tasks, and all require human annotations for evaluation. In this study, we demonstrate that annotations for this task can be harvested at scale from existing corpora, in a fully automatic manner. On a dataset of 1.8 million sentences thus derived, we propose a network architecture that encodes the context and seed term separately before suggesting alternative terms. The context encoder in this architecture can be easily extended by incorporating seed-aware attention. Our experiments demonstrate that competitive results are achieved with appropriate choices of context encoder and attention scoring function.