Year: 2021
Type: report
Abstract: 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 computationally tractable medium. Graph-structured, embedding-based quasilinguistic representations can support formal and informal reasoning, human and inter-agent communication, and the development of scalable quasilinguistic corpora with characteristics of both literatures and associative memory. To achieve human-like intellectual competence, machines must be fully literate, able not only to read and learn, but to write things worth retaining as contributions to collective knowledge. In support of this goal, QNR-based systems could translate and process natural language corpora to support the aggregation, refinement, integration, extension, and application of knowledge at scale. Incremental development of QNRbased models can build on current methods in neural machine learning, and as systems mature, could potentially complement or replace today’s opaque, error-prone “foundation models” with systems that are more capable, interpretable, and epistemically reliable. Potential applications and implications are broad.
Author: Drexler, EK
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: DeepMind
OpenAlex ID: W7225215148