Revisit Systematic Generalization via Meaningful Learning
arXiv:2003.06658
Abstract
Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to optimistic results. We revisit this controversial topic from the perspective of meaningful learning, an exceptional capability of humans to learn novel concepts by connecting them with known ones. We reassess the compositional skills of sequence-to-sequence models conditioned on the semantic links between new and old concepts. Our observations suggest that models can successfully one-shot generalize to novel concepts and compositions through semantic linking, either inductively or deductively. We demonstrate that prior knowledge plays a key role as well. In addition to synthetic tests, we further conduct proof-of-concept experiments in machine translation and semantic parsing, showing the benefits of meaningful learning in applications. We hope our positive findings will encourage excavating modern neural networks' potential in systematic generalization through more advanced learning schemes.
arXiv commentAccepted to the Fifth BlackboxNLP in EMNLP 2022
References in corpus (10)
- Efficient Estimation of Word Representations in Vector Space
- Sequence to Sequence Learning with Neural Networks
- On the difficulty of training Recurrent Neural Networks
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Convolutional Sequence to Sequence Learning
- Exploiting Similarities among Languages for Machine Translation
- Pay Less Attention with Lightweight and Dynamic Convolutions
- Improving Text-to-SQL Evaluation Methodology
- Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
- Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation