TL;DR
This paper presents a joint parsing model for syntax and semantics that leverages rich annotations to achieve state-of-the-art results across multiple languages, revealing linguistic patterns at the interface.
Contribution
It introduces a novel joint parsing architecture that effectively combines syntactic and semantic analysis using the UDS dataset, outperforming previous methods.
Findings
Achieves state-of-the-art results in syntax and semantics parsing.
Identifies linguistic patterns supported by theory at the syntax-semantics interface.
Demonstrates successful generalization across 8 languages.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
