NL2LTL -一个Python包，用于将自然语言(NL)指令转换为线性时间逻辑(LTL)公式

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI:10.1609/aaai.v37i13.27068

Francesco Fuggitti, T. Chakraborti

{"title":"NL2LTL -一个Python包，用于将自然语言(NL)指令转换为线性时间逻辑(LTL)公式","authors":"Francesco Fuggitti, T. Chakraborti","doi":"10.1609/aaai.v37i13.27068","DOIUrl":null,"url":null,"abstract":"This is a demonstration of our newly released Python package NL2LTL which leverages the latest in natural language understanding (NLU) and large language models (LLMs) to translate natural language instructions to linear temporal logic (LTL) formulas. This allows direct translation to formal languages that a reasoning system can use, while at the same time, allowing the end-user to provide inputs in natural language without having to understand any details of an underlying \nformal language. The package comes with support for a set of default LTL patterns, corresponding to popular DECLARE templates, but is also fully extensible to new formulas and user inputs. The package is open-source and is free to use for the AI community under the MIT license. Open Source: https://github.com/IBM/nl2ltl. Video Link: https://bit.ly/3dHW5b1","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"21 1","pages":"16428-16430"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"NL2LTL - a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas\",\"authors\":\"Francesco Fuggitti, T. Chakraborti\",\"doi\":\"10.1609/aaai.v37i13.27068\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This is a demonstration of our newly released Python package NL2LTL which leverages the latest in natural language understanding (NLU) and large language models (LLMs) to translate natural language instructions to linear temporal logic (LTL) formulas. This allows direct translation to formal languages that a reasoning system can use, while at the same time, allowing the end-user to provide inputs in natural language without having to understand any details of an underlying \\nformal language. The package comes with support for a set of default LTL patterns, corresponding to popular DECLARE templates, but is also fully extensible to new formulas and user inputs. The package is open-source and is free to use for the AI community under the MIT license. Open Source: https://github.com/IBM/nl2ltl. Video Link: https://bit.ly/3dHW5b1\",\"PeriodicalId\":74506,\"journal\":{\"name\":\"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence\",\"volume\":\"21 1\",\"pages\":\"16428-16430\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1609/aaai.v37i13.27068\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/aaai.v37i13.27068","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 5

摘要

这是我们最新发布的Python包NL2LTL的演示，它利用最新的自然语言理解(NLU)和大型语言模型(llm)将自然语言指令转换为线性时间逻辑(LTL)公式。这允许直接翻译为推理系统可以使用的形式语言，同时允许最终用户以自然语言提供输入，而无需了解底层形式语言的任何细节。该包支持一组默认的LTL模式，与流行的DECLARE模板相对应，但也可以完全扩展到新的公式和用户输入。该软件包是开源的，可以在MIT许可下免费用于AI社区。开源:https://github.com/IBM/nl2ltl。视频链接:https://bit.ly/3dHW5b1

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

NL2LTL - a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas

This is a demonstration of our newly released Python package NL2LTL which leverages the latest in natural language understanding (NLU) and large language models (LLMs) to translate natural language instructions to linear temporal logic (LTL) formulas. This allows direct translation to formal languages that a reasoning system can use, while at the same time, allowing the end-user to provide inputs in natural language without having to understand any details of an underlying formal language. The package comes with support for a set of default LTL patterns, corresponding to popular DECLARE templates, but is also fully extensible to new formulas and user inputs. The package is open-source and is free to use for the AI community under the MIT license. Open Source: https://github.com/IBM/nl2ltl. Video Link: https://bit.ly/3dHW5b1

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence

自引率

0.00%

发文量