Tree (set theory)

Architecture

Tree structure

Inference

Multi-task learning

Hierarchy

Mathematics

Visual arts

Mathematical analysis

Artificial intelligence

Management

Natural language

Economics

Parsing

Inductive bias

Binary tree

Programming language

Natural language processing

Computer science

Task (project management)

Theoretical computer science

Market economy

Artificial neural network

arXiv (Cornell University)

Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger constituent ends, all of the smaller constituents that are nested within it must also be closed. While the standard LSTM architecture allows different neurons to track information at different time scales, it does not have an explicit bias towards modeling a hierarchy of constituents. This paper proposes to add such an inductive bias by ordering the neurons; a vector of master input and forget gates ensures that when a given neuron is updated, all the neurons that follow it in the ordering are also updated. Our novel recurrent architecture, ordered neurons LSTM (ON-LSTM), achieves good performance on four different tasks: language modeling, unsupervised parsing, targeted syntactic evaluation, and logical inference.

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks