Recently, many datasets have been proposed to test the systematic generalization ability of neural networks. The companion baseline Transformers, typically trained with default hyper …
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose …
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination …
Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing …
S An, Z Lin, Q Fu, B Chen, N Zheng, JG Lou… - arXiv preprint arXiv …, 2023 - arxiv.org
Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence. The AI community mainly studies this …
Y Yin, J Zeng, Y Li, F Meng, J Zhou… - Proceedings of the 61st …, 2023 - aclanthology.org
Existing neural models have difficulty generalizing to unseen combinations of seen components. To achieve compositional generalization, models are required to consistently …
In this work, we focus on the task of generating SPARQL queries from natural language questions, which can then be executed on Knowledge Graphs (KGs). We assume that gold …
Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a …
Human linguistic capacity is often characterized by compositionality and the generalization it enables--human learners can produce and comprehend novel complex expressions by …