No free lunch in linguistics or machine learning

Pater’s (2019) target article proposes that neural networks will provide theories of learning that generative grammar lacks. We argue that his enthusiasm is premature since the biases of neural networks are largely unknown, and he disregards decades of work on machine learning and learnability. Learning biases form a two-way street: all learners have biases, and those biases constrain the space of learnable grammars in mathematically measurable ways. Analytical methods from the related fields of computational learning theory and grammatical inference allow one to study language learning, neural networks, and linguistics at an appropriate level of abstraction. The only way to satisfy our hunger and to make progress on the science of language learning is to confront these core issues directly

Abstraction · Active learning (machine learning) · Algorithmic learning theory · Cognitive science · Computational linguistics · Epistemology · Generative grammar · Grammar · Language acquisition · Learnability · Linguistics · Natural language processing · Rule-based machine translation · Artificial Intelligence · Computer Science · Natural Language Processing Techniques · Philosophy · Psychology · Text Readability and Simplification

• Gradient morphophonology

  Open Access•Adam Mccollum•Proceedings of the Annual…•2019

  Add to list