Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

@inproceedings{Krishnamurthy2017NeuralSP,
  title={Neural Semantic Parsing with Type Constraints for Semi-Structured Tables},
  author={Jayant Krishnamurthy and Pradeep Dasigi and Matt Gardner},
  booktitle={EMNLP},
  year={2017}
}
We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed logical forms; and (2) an entity embedding and linking module that identifies entity mentions while generalizing across tables. We also introduce a novel method for training our neural model with question-answer supervision. On the… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • On the WIKITABLEQUESTIONS data set, our parser achieves a state-of-theart accuracy of 43.3% for a single model and 45.9% for a 5-model ensemble, improving on the best prior score of 38.7% set by a 15-model ensemble.
  • On this data set, our parser achieves a question answering accuracy of 43.3% and an ensemble of 5 parsers achieves 45.9%, both of which outperform the previous state-of-the-art of 38.7% set by an ensemble of 15 models (Haug et al., 2017).

Citations

Publications citing this paper.
SHOWING 1-10 OF 65 CITATIONS

It was the training data pruning too!

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Execution-Guided Neural Program Decoding

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Question Generation from SQL Queries Improves Neural Semantic Parsing

  • EMNLP
  • 2018
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 22 Citations per year from 2017 through 2019