Retrieval-Augmented Semantic Parsing: Using Large Language Models to Improve Generalization
Open-domain semantic parsing remains a challenging task, as models often rely on heuristics and struggle to handle unseen concepts. In this paper, we investigate the potential of large language models (LLMs) for this task and introduce Retrieval-Augmented Semantic Parsing (RASP), a simple yet effective approach that integrates external lexical knowledge into the parsing process. Our experiments not only show that LLMs outperform previous encoder-decoder baselines for semantic parsing, but that RASP further enhances their ability to predict unseen concepts, nearly doubling the performance of previous models on out-of-distribution concepts. These findings highlight the promise of leveraging large language models and retrieval mechanisms for robust and open-domain semantic parsing.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderRetrievalSemantic ParsingSimilar Papers 제목 키워드 기반
RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing
While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory has a number of benefits from accuracy imp…
Question AnsweringRetrievalSemantic ParsingImproving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning
We focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation. Motivated by challenges related to the size of commercial database schemata and the deployability of business intelligence …
In-Context LearningRetrievalRetrieval-augmented GenerationSemantic Parsing+2KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Kn…
Graph Question AnsweringAnswer GenerationKnowledge GraphsSemantic ParsingTabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations
Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While …
Question AnsweringXRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing
In-context learning using large language models has recently shown surprising results for semantic parsing tasks such as Text-to-SQL translation. Prompting GPT-3 or Codex using several examples of question-SQL pairs can …
In-Context LearningRetrievalSemantic ParsingText to SQL+3