Global Neural CCG Parsing with Optimality Guarantees
This work addresses the challenge of efficient and accurate parsing for natural language processing, offering a novel method that is incremental but provides strong performance gains.
The paper tackles the problem of incorporating global features into neural CCG parsing without sacrificing optimality guarantees, achieving a 0.4 F1 improvement in state-of-the-art accuracy and finding optimal parses for 99.9% of held-out sentences while exploring only 190 subtrees on average.
We introduce the first global recursive neural parsing model with optimality guarantees during decoding. To support global features, we give up dynamic programs and instead search directly in the space of all possible subtrees. Although this space is exponentially large in the sentence length, we show it is possible to learn an efficient A* parser. We augment existing parsing models, which have informative bounds on the outside score, with a global model that has loose bounds but only needs to model non-local phenomena. The global model is trained with a new objective that encourages the parser to explore a tiny fraction of the search space. The approach is applied to CCG parsing, improving state-of-the-art accuracy by 0.4 F1. The parser finds the optimal parse for 99.9% of held-out sentences, exploring on average only 190 subtrees.