ავტორი: Aliyu Ahmed Abubakar
ორგანიზაცია: Kaduna State University Wuhan University


საკვანძო სიტყვები: Commonsense Reasoning, Knowledge Resource, Natural Language Processing (NLP), Artificial Intelligence (AI)
აბსტრაქტი. People use knowledge and commonsense reasoning for daily activities and survival. However, providing machines with such humanly knowledge and commonsense reasoning experiences has remained a vague target of artificial intelligence researchers for years. This report surveys knowledge and commonsense reasoning for Natural Language Processing with the aim of providing an overview of the benchmarks, knowledge resources, state of the art and inference approach toward knowledge and commonsense reasoning for natural language processing.


1. Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., & Ives, Z. (2007). DBpedia: A Nucleus for a Web of Open Data. The Semantic Web Challenge (pp. 722-735). Busan, Korea: Springer Berlin Heidelberg.
2. Baud, R. H., Rassinoux, A. M., Lovis, C., Wagner, J., Griesser, V., Michel, P. A., & Scherrer, J. R. (1996). Knowledge sources for Natural Language Processing. Proceedings of the AMIA Annual Fall Symposium (pp. 70-74). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2233211/.
3. Bhagavatula, C., Bras, R. L., Malaviya, C., Sakaguchi, K., Holtzman, A., Rashkin, H., . . . Choi, Y. (2020). Abductive commonsense reasoning. 8th International Conference on Learning Representations, ICLR (pp. 26-30). Addis Ababa: OpenReview.net.
4. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008). Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge. The 2008 ACM SIGMOD International Conference on Management of Data (pp. 1247–1250). NY, USA: SIGMOD .
5. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., . . . Child, R. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems. 33: Annual Conference on Neural Information Processing Systems 2020. Virtual: NeurIPS 2020.
6. Cambria, E., Speer, R., Havasi, C., & & Hussain, A. (2010). SenticNet: A Publicly Available Semantic Resource for Opinion Mining. AAAI Fall Symposium on Commonsense Knowledge. Menlo Park, CA, USA: AAAI Press.
7. Chklovski, T. (2003). Learner: A System for Acquiring Commonsense Knowledge by Analogy. The 2nd International Conference on Knowledge Capture (K-CAP ’03), K-CAP ’03 (pp. 4-12). New York, NY, USA. : ACM.
8. Commonsenseknowledge. (n.d.). http://commonsensereasoning.org. Retrieved December 04, 2021, from www.commonsensereasoning.org: http://commonsensereasoning.org/
9. Davis, E., & Marcus, G. (2015). reasoning and commonsense knowledge in artificial Commonsense intelligence. Commun. ACM, 92–103.
10. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT.
11. Gehrmann, S., Adewumi, T., Aggarwal, K., Sasanka, P., Ammanamanchi, Anuoluwapo, A., . . . Emezue, C. (2021). The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics. New York: Amelia R&D.
12. Gupta, V. (2014). A Survey of Natural Language Processing Techniques. International Journal of Computer Science & Engineering Technology (IJCSET), 05(01).
13. Huang, C., He, W., & Liu, Y. (2021). Improving Unsupervised Commonsense Reasoning Using Knowledge-Enabled Natural Language Inference. Findings of the Association for Computational Linguistics, 4875-4885.
14. Lenat, D. B., & Guha, R. V. (1989). Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project. Boston, MA, USA: Addison-Wesley Longman Publishing Co., Inc.
15. Li, Z., Ding, X., & Liu, T. (2019). Story ending prediction by transferable BERT. Twenty- Eighth International Joint Conference on Artificial Intelligence, IJCAI (pp. 1800-1806). Macao China: ijcai.org.
16. Liu, H., & Singh, P. (2004). ConceptNet — A Practical Commonsense Reasoning Tool-Kit. BT Technology Journal, 211-226.
17. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M. S., Chen, D., . . . Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach.
18. Lourie, N., Bras, R. L., Bhagavatula, C., & Choi, Y. (2021). Rainbow: A Commonsense Reasoning Benchmark. Retrieved 12 06, 2021, from www.allenai.org: https://allenai.org/data/rainbow