QNRs: toward language for intelligent machines
<p>Impoverished syntax and nondifferentiable vocabularies make natural language a poor medium for neural representation learning and applications. Learned, quasilinguistic neural representations (QNRs) can upgrade words to embeddings and syntax to graphs to provide a more expressive and comput...
| 主要作者: | |
|---|---|
| 格式: | Report |
| 语言: | English |
| 出版: |
Future of Humanity Institute
2021
|