paper-with-me

홈 › Papers

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding

2023-05-31 · Parker Glenn, Parag Pravin Dakle, Preethi Raghavan

In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges. It becomes increasingly important to understand and remedy the points of failure as the performance of semantic parsing systems improve. We explore semantic parse correction with natural language feedback, proposing a new solution built on the success of autoregressive decoders in text-to-SQL tasks. By separating the semantic and syntactic difficulties of the task, we show that the accuracy of text-to-SQL parsers can be boosted by up to 26% with only one turn of correction with natural language. Additionally, we show that a T5-base model is capable of correcting the errors of a T5-large model in a zero-shot, cross-parser setting.

📄 PDF Abstract BibTeX arXiv:2305.19974

Code (1)

parkervg/destt5 공식 구현

Tasks

Semantic ParsingText to SQLText-To-SQL

Similar Papers 제목 키워드 기반

A Deep Architecture for Semantic Parsing

2014-04-29 · WS 2014 6 · Edward Grefenstette, Phil Blunsom, Nando de Freitas, Karl Moritz Hermann

Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries. This paper…

Semantic Parsing

"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation

2023-10-26 · Allyson Ettinger, Jena D. Hwang, Valentina Pyatkin, Chandra Bhagavatula 외

Large language models (LLMs) show amazing proficiency and fluency in the use of language. Does this mean that they have also acquired insightful linguistic knowledge about the language, to an extent that they can serve a…

Abstract Meaning RepresentationNatural Language QueriesSentence

NL-EDIT: Correcting semantic parse errors through natural language interaction

2021-03-26 · NAACL 2021 4 · Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney 외

We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to gener…

Semantic ParsingText to SQLText-To-SQL

Break It Down: A Question Understanding Benchmark

2020-01-31 · TACL 2020 1 · Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner 외

Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) f…

Open-Domain Question AnsweringQuestion AnsweringReading ComprehensionSemantic Parsing+1

Statistical Parsing for Logical Information Retrieval

2026-02-12 · Greg Coppola arxiv

In previous work (Coppola, 2024) we introduced the Quantified Boolean Bayesian Network (QBBN), a logical graphical model that implements the forward fragment of natural deduction (Prawitz, 1965) as a probabilistic factor…

Information Retrieval