Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction
This work addresses a specific challenge in natural language processing for linguists and NLP practitioners, representing an incremental improvement over existing methods.
The paper tackles the problem of coordination structure prediction by proposing a transition-based bubble parser that simultaneously identifies coordination structures and performs dependency-based syntactic analysis, achieving state-of-the-art results on the English Penn Treebank and GENIA corpus, particularly for sentences with complex coordination structures.
We propose a transition-based bubble parser to perform coordination structure identification and dependency-based syntactic analysis simultaneously. Bubble representations were proposed in the formal linguistics literature decades ago; they enhance dependency trees by encoding coordination boundaries and internal relationships within coordination structures explicitly. In this paper, we introduce a transition system and neural models for parsing these bubble-enhanced structures. Experimental results on the English Penn Treebank and the English GENIA corpus show that our parsers beat previous state-of-the-art approaches on the task of coordination structure prediction, especially for the subset of sentences with complex coordination structures.