Highlight

Semantic Parsing on Freebase from Question-Answer Pairs

A paper proposing a semantic parser that learns from question-answer pairs to scale up to Freebase.

Based on

Semantic Parsing on Freebase from Question-Answer Pairs

By Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang
Read original article →

The authors present a method for training a semantic parser using question-answer pairs, which outperforms previous state-of-the-art parsers. They tackle the challenge of narrowing down possible logical predicates by building a coarse mapping and using bridging operations.

The paper also introduces a new dataset of question-answer pairs.

Abstract

The authors present a method for training a semantic parser using question-answer pairs, which outperforms previous state-of-the-art parsers. They tackle the challenge of narrowing down possible logical predicates by building a coarse mapping and using bridging operations. The paper also introduces a new dataset of question-answer pairs.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

semantic parsingfreebasequestion answeringlogical formspredicate mappingKnowledge GraphsStructured ContentAI AgentsLarge Language Models
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources