Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Automatic Composition of ASP Programs from Natural Language Specifications (2403.04541v1)

Published 7 Mar 2024 in cs.AI

Abstract: This paper moves the first step towards automating the composition of Answer Set Programming (ASP) specifications. In particular, the following contributions are provided: (i) A dataset focused on graph-related problem specifications, designed to develop and assess tools for ASP automatic coding; (ii) A two-step architecture, implemented in the NL2ASP tool, for generating ASP programs from natural language specifications. NL2ASP uses neural machine translation to transform natural language into Controlled Natural Language (CNL) statements. Subsequently, CNL statements are converted into ASP code using the CNL2ASP tool. An experiment confirms the viability of the approach.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. The ASP system DLV2. In LPNMR, volume 10377 of LNCS, pages 215–221. Springer, 2017.
  2. Introducing ASP recipes and ASP chef. In ICLP Workshops, volume 3437 of CEUR Workshop Proceedings. CEUR-WS.org, 2023.
  3. Neural machine translation by jointly learning to align and translate. In ICLR, 2015.
  4. METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In IEEvaluation@ACL, pages 65–72. Association for Computational Linguistics, 2005.
  5. Solving puzzles described in english by automated translation to answer set programming and learning how to do that translation. In AAAI Fall Symposium: Advances in Cognitive Systems, volume FS-11-01 of AAAI Technical Report. AAAI, 2011.
  6. Sparql-qa-v2 system for knowledge base question answering. Expert Syst. Appl., 229(Part A):120383, 2023.
  7. Answer set programming at a glance. Commun. ACM, 54(12):92–103, 2011.
  8. Sealion: An eclipse-based IDE for answer-set programming with advanced debugging support. Theory Pract. Log. Program., 13(4-5):657–673, 2013.
  9. Asp-core-2 input language format. Theory Pract. Log. Program., 20(2):294–309, 2020.
  10. Github copilot AI pair programmer: Asset or liability? J. Syst. Softw., 203:111734, 2023.
  11. A tool for encoding controlled natural language specifications as ASP rules. In Datalog, volume 3203 of CEUR Workshop Proceedings, pages 188–201. CEUR-WS.org, 2022.
  12. Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia. In ISWC (2), volume 11779 of LNCS, pages 69–78. Springer, 2019.
  13. Semantical characterizations and complexity of equivalences in answer set programming. ACM Trans. Comput. Log., 8(3):17, 2007.
  14. Transforming controlled natural language biomedical queries into answer set programs. In BioNLP@HLT-NAACL, pages 117–124. Association for Computational Linguistics, 2009.
  15. Applications of answer set programming. AI Mag., 37(3):53–68, 2016.
  16. Ai-driven development is here: Should you worry? IEEE Softw., 39(2):106–110, 2022.
  17. Mark Chen et al. Evaluating large language models trained on code. CoRR, abs/2107.03374, 2021.
  18. An approach for representing answer sets in natural language. In DECLARE, volume 10997 of LNCS, pages 115–131. Springer, 2017.
  19. ASPIDE: integrated development environment for answer set programming. In LPNMR, volume 6645 of LNCS, pages 317–330. Springer, 2011.
  20. Answer Set Solving in Practice. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2012.
  21. Theory solving made easy with clingo 5. In ICLP (Technical Communications), volume 52 of OASIcs, pages 2:1–2:15. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2016.
  22. The seventh answer set programming competition: Design and results. Theory Pract. Log. Program., 20(2):176–204, 2020.
  23. The stable model semantics for logic programming. In ICLP/SLP, pages 1070–1080. MIT Press, 1988.
  24. Classical negation in logic programs and disjunctive databases. New Gener. Comput., 9(3/4):365–386, 1991.
  25. Clingraph: A system for asp-based visualization. CoRR, abs/2303.10118, 2023.
  26. Xinyu Hua and Lu Wang. PAIR: planning and iterative refinement in pre-trained transformers for long text generation. CoRR, abs/2010.02301, 2020.
  27. Leveraging large language models to generate answer set programs. In KR, pages 374–383, 2023.
  28. Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition. Prentice Hall series in artificial intelligence. Prentice Hall, Pearson Education International, 2009.
  29. Eirini Kalliamvakou. Research: quantifying github copilot’s impact on developer productivity and happiness, 2022.
  30. Tobias Kuhn. A survey and classification of controlled natural languages. Comput. Linguistics, 40(1):121–170, 2014.
  31. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. CoRR, abs/1910.13461, 2019.
  32. Systems, engineering environments, and competitions. AI Mag., 37(3):45–52, 2016.
  33. Vladimir Lifschitz. Answer Set Programming. Springer, 2019.
  34. Vladimir Lifschitz. Translating definitions into the language of logic programming: A case study. In ICLP Workshops, volume 3193 of CEUR Workshop Proceedings. CEUR-WS.org, 2022.
  35. Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. In AAAI, pages 2779–2785. AAAI Press, 2016.
  36. COGEX: A logic prover for question answering. In HLT-NAACL. The Association for Computational Linguistics, 2003.
  37. Improving coherence and consistency in neural sequence models with dual-system, neuro-symbolic reasoning. In NeurIPS, pages 25192–25204, 2021.
  38. Bleu: a method for automatic evaluation of machine translation. In ACL, pages 311–318. ACL, 2002.
  39. The impact of AI on developer productivity: Evidence from github copilot. CoRR, abs/2302.06590, 2023.
  40. Qald-9-plus: A multilingual dataset for question answering over dbpedia and wikidata translated by native speakers. In ICSC, pages 229–234. IEEE, 2022.
  41. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67, 2020.
  42. Rolf Schwitter. Specifying and verbalising answer set programs in controlled natural language. Theory Pract. Log. Program., 18(3-4):691–705, 2018.
  43. Felix Stahlberg. Neural machine translation: A review. J. Artif. Intell. Res., 69:343–418, 2020.
  44. Sequence to sequence learning with neural networks. In NIPS, pages 3104–3112, 2014.
  45. Lc-quad: A corpus for complex question answering over knowledge graphs. In ISWC (2), volume 10588 of LNCS, pages 210–218. Springer, 2017.
  46. Annotating answer-set programs in lana. Theory Pract. Log. Program., 12(4-5):619–637, 2012.
  47. Wiebke Wagner. Steven bird, ewan klein and edward loper: Natural language processing with python, analyzing text with the natural language toolkit - o’reilly media, beijing, 2009, ISBN 978-0-596-51649-9. Lang. Resour. Evaluation, 44(4):421–424, 2010.
  48. Transformers: State-of-the-art natural language processing. In EMNLP (Demos), pages 38–45. Association for Computational Linguistics, 2020.
  49. A skeleton-based model for promoting coherence among sentences in narrative story generation. In EMNLP, pages 4306–4315. Association for Computational Linguistics, 2018.
  50. A survey of deep learning techniques for neural machine translation. CoRR, abs/2002.07526, 2020.
  51. Coupling large language models with logic programming for robust and general reasoning from text. In ACL (Findings), pages 5186–5219. Association for Computational Linguistics, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Manuel Borroto (1 paper)
  2. Irfan Kareem (1 paper)
  3. Francesco Ricca (36 papers)
Citations (2)
View on Semantic Scholar