Sentence Structure and Word Relationship Modeling for Emphasis Selection
This work addresses a newly proposed task for enhancing text emphasis in short sentences, representing an incremental improvement over existing methods.
The paper tackled the emphasis selection task by proposing a framework that incorporates sentence structure and word relationship graphs, achieving superior performance compared to traditional sequence-only methods.
Emphasis Selection is a newly proposed task which focuses on choosing words for emphasis in short sentences. Traditional methods only consider the sequence information of a sentence while ignoring the rich sentence structure and word relationship information. In this paper, we propose a new framework that considers sentence structure via a sentence structure graph and word relationship via a word similarity graph. The sentence structure graph is derived from the parse tree of a sentence. The word similarity graph allows nodes to share information with their neighbors since we argue that in emphasis selection, similar words are more likely to be emphasized together. Graph neural networks are employed to learn the representation of each node of these two graphs. Experimental results demonstrate that our framework can achieve superior performance.