A Sequence Labeling Method for First-order Logic Representation
DOI:
https://doi.org/10.54097/ehss.v8i.4287Keywords:
Sequence-to-sequence model; Logic representation; Generative Model; Natural Language Processing.Abstract
Extracting logic knowledge is an important part of natural language understanding. This study introduces a new dataset for the purpose of measuring the model's ability to transfer natural language to logic form. Since logic represents how various concepts infer and reason from/to each other, it is essential to learn logical structure in any form of language while trying to comprehend its meaning of it. There have recently been many interests in deploying machine learning and deep learning methods for extracting logical knowledge and representing logic from natural language. The promising generative model that applied to recent sequence labeling work is used in the task of representing logic. Experiments have shown that generative methods can extract logic form from natural language texts. To be more specific, a sequence-to-sequence model is quite a convenient option when it deals with extraction tasks. The model provided in this study would be inspiring for future studies to work out more efficient solutions.
Downloads
References
Moore R C. Logic and representation. Center for the Study of Language (CSLI), 1995.
Baral C, Gelfond M. Logic programming and knowledge representation. The Journal of Logic Programming, 1994, 19: 73-148.
Gershman S J. The successor representation: its computational logic and neural substrates. Journal of Neuroscience, 2018, 38(33): 7193-7200.
Thompson A, Mooney J, Tang R. Learning to parse natural language database queries into logical form. 1997.
Settles B, Craven M. An analysis of active learning strategies for sequence labeling tasks. proceedings of EMNLP. 2008: 1070-1079.
Nguyen N, Guo Y. Comparisons of sequence labeling algorithms and extensions. Proceedings of the 24th ICML. 2007: 681-688.
Chowdhary K R. Natural language processing. Fundamentals of artificial intelligence, 2020: 603-649.
Cohen S B, Smith N A. Variational inference for grammar induction with prior knowledge. Proceedings of the ACL-IJCNLP 2009 Conference Short Papers. 2009: 1-4.
Ni J, Rossiello G, Gliozzo A, Florian R. A Generative Model for Relation Extraction and Classification. ArXiv, abs/2202.13229, 2022.
Zalta, Edward N, Gottlob Frege. The Stanford Encyclopedia of Philosophy (Fall 2022 Edition), Edward N. Zalta (ed.), 2022.
Quine O. Peano as logician, Hist. Philos, Logic, 1987, 8(1): 15-24.
Russell B. Introduction to Mathematical Philosophy, London: George Allen & Unwin, 1919.
Church A. Russellian Simple Type Theory, Proceedings and Addresses of the American Philosophical Association, 1974, 47: 21–33.
Quine O. Word and Object, Cambridge: MIT Press, 1960.
Woods W A. 1973. Progress in natural language understanding: An application to lunar geology. Proceedings of the National Computer Conference and Exposition. 1973: 441–450.
Zhao K, Huang L. Type-driven incremental semantic parsing with polymorphism. Proceedings of the NAACL, 2015: 1416–1421.
Thomspon C A, Mooney J. Acquiring word-meaning mappings for natural language interfaces. JAIR, 2003, 18:1–44.
Abzianidze L, Kogkalidis K. A Logic-Based Framework for Natural Language Inference in Dutch. CLIN Journal, 2021, 11: 35-58.
Zhu Z et al. Neural-Symbolic Models for Logical Queries on Knowledge Graphs. ICML 2022.
Evans R et al. Can Neural Networks Understand Logical Entailment? ArXivabs/1802.08535, 2018.
Raffel C et al. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer, JMLR, 2020, 21(140):1−67.
Tom B B et al. Language models are few-shot learners. Proceedings of the 34th International Conference on Neural Information Processing Systems. Curran Associates Inc., 2020, 1877–1901.
Li D, Lapata M. Language to Logical Form with Neural Attention. Proceedings of the 54th ACL, 2016: 33–43.
Lewis M et al. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. Proceedings of the 58th ACL, 2020: 7871–7880.
Trisedya B D, Weikum G, Qi J, Zhang R. Neural relation extraction for knowledge base enrichment. Proceedings of the 57th ACL, 2019: 229-240.
Josifoski M, Nicola D C, Peyrard M, West R. GenIE: Generative Information Extraction. Proceedings of the NACCL: Human Language Technologies, 2022: 4626-4643.
Wolf T et al. Transformers: State-of-the-Art Natural Language Processing. EMNLP, 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
