2019
DOI: 10.48550/arxiv.1909.12764
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Improving Semantic Parsing with Neural Generator-Reranker Architecture

Abstract: Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional methods. Although neural semantic parsers appear to have relatively high recall using large beam sizes, there is room for improvement with respect to onebest precision. In this work, we propose a generator-reranker architecture for semantic parsing. The generator produces a li… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 29 publications
0
0
0
Order By: Relevance
“…Generator-Reranker architecture is proposed by Inan et al [129]. The generator produces a list of potential candidates, and the reranker ranks these candidates based on the similarity between each candidate and the input sentence.Lu et al [130] have proposed the recall-oriented information extraction method.…”
mentioning
confidence: 99%
“…Generator-Reranker architecture is proposed by Inan et al [129]. The generator produces a list of potential candidates, and the reranker ranks these candidates based on the similarity between each candidate and the input sentence.Lu et al [130] have proposed the recall-oriented information extraction method.…”
mentioning
confidence: 99%