-
SPAGHETTI: Open-Domain Question Answering
SPAGHETTI: A hybrid open-domain question-answering system that combines semantic parsing and information retrieval to handle structured and unstructured data. -
Spider-CG: A dataset for compositional generalization in text-to-SQL
A dataset for compositional generalization in text-to-SQL -
Improving Generalization in Language Model-Based Text-to-SQL
Two simple semantic boundary-based techniques to improve the generalization of language model-based text-to-SQL -
Task-Oriented Semantic Parsing
Task-oriented, conversational assistants typically use semantic parsers to map textual utterances to structured frames executable by downstream components. -
On The Ingredients of an Effective Zero-shot Semantic Parser
Semantic parsers map natural language utterances into meaning representations (e.g. programs). Such models are typically bottle-necked by the paucity of training data due to the... -
WebQuestions
The task of Question Answering over Linked Data (QALD) has received increased attention over the last years (see the surveys [14] and [36]). The task consists in mapping natural... -
NL2BASH: A corpus and semantic parser for natural language interface to the L...
The NL2BASH dataset is a corpus and semantic parser for natural language interface to the Linux operating system.
