The Fast and the Flexible: training neural networks to learn to follow instructions from small data
| Autor: | Leonandya, R., Hupkes, D., Bruni, E., Kruszewski, G., Dobnik, S., Chatzikyriakidis, S., Demberg, V. |
|---|---|
| Přispěvatelé: | ILLC (FNWI), Language and Computation (ILLC, FNWI/FGw), Brain and Cognition, Logic and Language (ILLC, FNWI/FGw), Faculty of Science |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Structure (mathematical logic)
FOS: Computer and information sciences Vocabulary Computer Science - Computation and Language Small data Artificial neural network Inductive bias business.industry Computer science media_common.quotation_subject Contrast (statistics) Machine learning computer.software_genre Task (project management) Offline learning Artificial intelligence business computer Computation and Language (cs.CL) media_common |
| Zdroj: | Proceedings of the 13th International Conference on Computational Semantics-Long Papers: IWCS 2019 : 23-27 May, 2019, University of Gothenburg, Gothenburg, Sweden, 223-234 STARTPAGE=223;ENDPAGE=234;TITLE=Proceedings of the 13th International Conference on Computational Semantics-Long Papers IWCS (1) |
| Popis: | Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to learn from. Work in the past has relied on hand-coded components or manually engineered features to provide strong inductive biases that make learning in such situations possible. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|