This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.
Comment: In Pascal Hitzler, Md Kamruzzaman Sarker (eds.), Neuro-Symbolic Artificial Intelligence: The State of the Art. Frontiers in Artificial Intelligence and Applications Vol. 342, IOS Press, Amsterdam, 2022. arXiv admin note: text overlap with arXiv:2003.04707