EMNLP Findings2020
Accurate Polyglot Semantic Parsing With DAG Grammars
Federico Fancellu, Ákos Kádár, Ran Zhang, Afsaneh Fazly
Abstract
Semantic parses are directed acyclic graphs (DAGs), but in practice most parsers treat them as strings or trees, mainly because models that predict graphs are far less understood. This simplification, however, comes at a cost: there is no guarantee that the output is a well-formed graph. A recent work by Fancellu et al. (2019) addressed this problem by proposing a graphaware sequence model that utilizes a DAG grammar to guide graph generation. We significantly improve upon this work, by proposing a simpler architecture as well as more efficient training and inference algorithms that can always guarantee the well-formedness of the generated graphs. Importantly, unlike Fancellu et al., our model does not require language-specific features, and hence can harness the inherent ability of DAG-grammar parsing in multilingual settings. We perform monolingual as well as multilingual experiments on the Parallel Meaning Bank (Abzianidze et al., 2017). Our parser outperforms previous graph-aware models by a large margin, and closes the performance gap between string-based and DAG-grammar parsing.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic ParsingDora Jambor, Dzmitry BahdanauACL 2022
- Dependency Graph Parsing as Sequence LabelingAna Ezquerro, David Vilares, Carlos Gómez-RodríguezEMNLP 2024 · 1 citation
- DRTS Parsing with Structure-Aware Encoding and DecodingQiankun Fu, Yue Zhang, Jiangming Liu, Meishan ZhangACL 2020 · 8 citations
- Grammar-Constrained Neural Semantic Parsing with LR ParsersArtur Baranowski, Nico HochgeschwenderACL Findings 2021 · 6 citations
- Graph-Based Decoding for Task Oriented Semantic ParsingJeremy R. Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He et al.EMNLP Findings 2021 · 1 citation
