Syntactic Structure from Deep Learning
Authors:
Top Cited Papers
- 14 January 2021
- journal article
- research article
- Published by Annual Reviews in Annual Review of Linguistics
- Vol. 7 (1) , 195-212
Abstract
Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation. This success has sparked interest in probing whether these models are inducing human-like grammatical knowledge from the raw data they are exposed to and, consequently, whether they can shed new light on long-standing debates concerning the innate structure necessary for language acquisition. In this article, we survey representative studies of the syntactic abilities of deep networks and discuss the broader implications that this work has for theoretical linguistics.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- The faculty of language: what's special about it?Cognition, 2005
- The Faculty of Language: What Is It, Who Has It, and How Did It Evolve?Science, 2002
- Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal CortexScience, 2001
- Connectionist Natural Language Processing: The State of the ArtCognitive Science, 1999
- Memory Limitations and Structural Forgetting: The Perception of Complex Ungrammatical Sentences as GrammaticalLanguage and Cognitive Processes, 1999
- Long Short-Term MemoryNeural Computation, 1997
- Broken agreementCognitive Psychology, 1991
- Connectionism and cognitive architecture: A critical analysisCognition, 1988
- On language and connectionism: Analysis of a parallel distributed processing model of language acquisitionCognition, 1988
- Rules and representationsBehavioral and Brain Sciences, 1980