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

Identification of Entailment and Contradiction Relations between Natural Language Sentences: A Neurosymbolic Approach (2405.01259v1)

Published 2 May 2024 in cs.AI and cs.CL

Abstract: Natural language inference (NLI), also known as Recognizing Textual Entailment (RTE), is an important aspect of natural language understanding. Most research now uses machine learning and deep learning to perform this task on specific datasets, meaning their solution is not explainable nor explicit. To address the need for an explainable approach to RTE, we propose a novel pipeline that is based on translating text into an Abstract Meaning Representation (AMR) graph. For this we use a pre-trained AMR parser. We then translate the AMR graph into propositional logic and use a SAT solver for automated reasoning. In text, often commonsense suggests that an entailment (or contradiction) relationship holds between a premise and a claim, but because different wordings are used, this is not identified from their logical representations. To address this, we introduce relaxation methods to allow replacement or forgetting of some propositions. Our experimental results show this pipeline performs well on four RTE datasets.

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 (30)
  1. M. Alabbas. Textual Entailment for Modern Standard Arabic. PhD thesis, University of Manchester, 08 2013.
  2. A survey on textual entailment: Benchmarks, approaches and applications. In 2022 13th International Conference on Information and Communication Systems (ICICS), pages 328–336, 2022. 10.1109/ICICS55353.2022.9811200.
  3. Towards artificial argumentation. AI Mag., 38(3):25–36, 2017. 10.1609/AIMAG.V38I3.2704. URL https://doi.org/10.1609/aimag.v38i3.2704.
  4. Abstract Meaning Representation for sembanking. In A. Pareja-Lora, M. Liakata, and S. Dipper, editors, Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 178–186, Sofia, Bulgaria, Aug. 2013. Association for Computational Linguistics. URL https://aclanthology.org/W13-2322.
  5. Arabic logic textual entailment with feature extraction and combination. In A. Abraham, A. K. Cherukuri, P. Melin, and N. Gandhi, editors, Intelligent Systems Design and Applications, pages 400–409, Cham, 2020. Springer International Publishing. ISBN 978-3-030-16660-1.
  6. J. Bos. Squib: Expressive power of Abstract Meaning Representations. Computational Linguistics, 42(3):527–535, Sept. 2016. 10.1162/COLI_a_00257. URL https://aclanthology.org/J16-3006.
  7. J. Bos and K. Markert. Recognising textual entailment with logical inference. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT ’05, page 628–635, USA, 2005. Association for Computational Linguistics. 10.3115/1220575.1220654. URL https://doi.org/10.3115/1220575.1220654.
  8. A large annotated corpus for learning natural language inference. CoRR, abs/1508.05326, 2015. URL http://arxiv.org/abs/1508.05326.
  9. e-snli: Natural language inference with natural language explanations. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018. URL https://proceedings.neurips.cc/paper_files/paper/2018/file/4c7a167bb329bd92580a99ce422d6fa6-Paper.pdf.
  10. D. Chanin and A. Hunter. Neuro-symbolic commonsense social reasoning. arXiv preprint arXiv:2303.08264, 2023.
  11. Minimal recursion semantics: An introduction. Reseach On Language And Computation, 3:281–332, 07 2005. 10.1007/s11168-006-6327-9.
  12. Machine learning challenges. evaluating predictive uncertainty, visual object classification, and recognising tectual entailment: First pascal machine learning challenges workshop, mlcw 2005, southampton, uk, april 11-13, 2005, revised selected papers, chapter the pascal recognising textual entailment challenge, 2006.
  13. A lexical alignment model for probabilistic textual entailment. In Proceedings of the First International Conference on Machine Learning Challenges: Evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment, MLCW’05, page 287–298, Berlin, Heidelberg, 2005. Springer-Verlag. ISBN 3540334270. 10.1007/11736790_16. URL https://doi.org/10.1007/11736790_16.
  14. OntoNotes: The 90% solution. In R. C. Moore, J. Bilmes, J. Chu-Carroll, and M. Sanderson, editors, Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, pages 57–60, New York City, USA, June 2006. Association for Computational Linguistics. URL https://aclanthology.org/N06-2015.
  15. MonaLog: a lightweight system for natural language inference based on monotonicity. In A. Ettinger, G. Jarosz, and J. Pater, editors, Proceedings of the Society for Computation in Linguistics 2020, pages 334–344, New York, New York, Jan. 2020. Association for Computational Linguistics. URL https://aclanthology.org/2020.scil-1.40.
  16. PySAT: A Python toolkit for prototyping with SAT oracles. In SAT, pages 428–437, 2018. 10.1007/978-3-319-94144-8_26. URL https://doi.org/10.1007/978-3-319-94144-8_26.
  17. Recognizing textual entailment using lexical similarity. In Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment, pages 73–76. Citeseer, 2005.
  18. Discourse Representation Theory, pages 125–394. Springer Netherlands, Dordrecht, 2011. ISBN 978-94-007-0485-5. 10.1007/978-94-007-0485-5_3. URL https://doi.org/10.1007/978-94-007-0485-5_3.
  19. R. T. Kasper. A flexible interface for linking applications to Penman’s sentence generator. In Speech and Natural Language: Proceedings of a Workshop Held at Philadelphia, Pennsylvania, February 21-23, 1989, 1989. URL https://aclanthology.org/H89-1022.
  20. P. Kingsbury and M. Palmer. From TreeBank to PropBank. In M. González Rodríguez and C. P. Suarez Araujo, editors, Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02), Las Palmas, Canary Islands - Spain, May 2002. European Language Resources Association (ELRA). URL http://www.lrec-conf.org/proceedings/lrec2002/pdf/283.pdf.
  21. I. Langkilde and K. Knight. Generation that exploits corpus-based statistical knowledge. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1, pages 704–710, Montreal, Quebec, Canada, Aug. 1998. Association for Computational Linguistics. 10.3115/980845.980963. URL https://aclanthology.org/P98-1116.
  22. Maximum bayes smatch ensemble distillation for AMR parsing. CoRR, abs/2112.07790, 2021. URL https://arxiv.org/abs/2112.07790.
  23. SemEval-2014 task 1: Evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment. In P. Nakov and T. Zesch, editors, Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 1–8, Dublin, Ireland, Aug. 2014. Association for Computational Linguistics. 10.3115/v1/S14-2001. URL https://aclanthology.org/S14-2001.
  24. Sympy: symbolic computing in python. PeerJ Computer Science, 3:e103, Jan. 2017. ISSN 2376-5992. 10.7717/peerj-cs.103. URL https://doi.org/10.7717/peerj-cs.103.
  25. Design and realization of a modular architecture for textual entailment. Natural Language Engineering, 21(2):167 – 200, 2015. 10.1017/S1351324913000351. URL https://www.scopus.com/inward/record.uri?eid=2-s2.0-84925636275&doi=10.1017%2fS1351324913000351&partnerID=40&md5=3222bae9c46a9e43ee47dfbcd459be61. Cited by: 20; All Open Access, Green Open Access.
  26. Recognizing textual entailment: A review of resources, approaches, applications, and challenges. ICT Express, 2023. ISSN 2405-9595. https://doi.org/10.1016/j.icte.2023.08.012. URL https://www.sciencedirect.com/science/article/pii/S2405959523001145.
  27. N. Reimers and I. Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11 2019. URL http://arxiv.org/abs/1908.10084.
  28. Reasoning about entailment with neural attention. In International Conference on Learning Representations (ICLR), February 2016.
  29. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122. Association for Computational Linguistics, 2018. URL http://aclweb.org/anthology/N18-1101.
  30. A. Wotzlaw and R. Coote. A logic-based approach for recognizing textual entailment supported by ontological background knowledge. CoRR, abs/1310.4938, 2013. URL http://arxiv.org/abs/1310.4938.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Xuyao Feng (1 paper)
  2. Anthony Hunter (28 papers)
Citations (2)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets