Joint Universal Syntactic and Semantic Parsing
This work addresses the challenge of balancing high performance in both syntax and semantics for natural language processing, with incremental improvements in joint modeling.
The paper tackles the trade-off between syntactic and semantic parsing performance by exploring joint models using the Universal Decompositional Semantics dataset, achieving state-of-the-art results in both Universal Dependencies and UDS formalisms and showing generalization across 8 languages.
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other. This trade-off contradicts the large body of research focusing on the rich interactions at the syntax-semantics interface. We explore multiple model architectures which allow us to exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics (UDS) dataset, jointly parsing Universal Dependencies and UDS to obtain state-of-the-art results in both formalisms. We analyze the behaviour of a joint model of syntax and semantics, finding patterns supported by linguistic theory at the syntax-semantics interface. We then investigate to what degree joint modeling generalizes to a multilingual setting, where we find similar trends across 8 languages.