Corpus ID: 9060725

Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge

@inproceedings{Gardner2017OpenVocabularySP,
  title={Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge},
  author={Matt Gardner and J. Krishnamurthy},
  booktitle={AAAI},
  year={2017}
}
Traditional semantic parsers map language onto compositional, executable queries in a fixed schema. This mapping allows them to effectively leverage the information contained in large, formal knowledge bases (KBs, e.g., Freebase) to answer questions, but it is also fundamentally limiting---these semantic parsers can only assign meaning to language that falls within the KB's manually-produced schema. Recently proposed methods for open vocabulary semantic parsing overcome this limitation by… Expand
23 Citations
Building a Neural Semantic Parser from a Domain Ontology
  • 5
  • PDF
Syntax-mediated semantic parsing
Lifecycle of neural semantic parsing
Universal Semantic Parsing
  • 61
  • PDF
Dependency-based Hybrid Trees for Semantic Parsing
  • 5
  • PDF
Weakly-supervised Neural Semantic Parsing with a Generative
  • Ranker
  • 2018
  • PDF
Learning Structured Natural Language Representations for Semantic Parsing
  • 56
  • PDF
Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
  • 39
  • PDF
Weakly-supervised Neural Semantic Parsing with a Generative Ranker
  • 9
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 53 REFERENCES
Scaling Semantic Parsers with On-the-Fly Ontology Matching
  • 289
  • PDF
Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary
  • 32
  • PDF
Weakly Supervised Training of Semantic Parsers
  • 138
  • PDF
Joint Syntactic and Semantic Parsing with Combinatory Categorial Grammar
  • 34
  • PDF
Transforming Dependency Structures to Logical Forms for Semantic Parsing
  • 127
  • PDF
Large-scale Semantic Parsing without Question-Answer Pairs
  • 181
  • PDF
Learning to Parse Database Queries Using Inductive Logic Programming
  • 559
  • PDF
...
1
2
3
4
5
...