William Cooper Merrill

This work attempts to explain the types of computation that neural networks can perform by relating them to automata, as well as the relationship between neural networks and natural language grammar. Expand

This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Expand

We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Expand

We develop a formal hierarchy of the expressive capacity of RNN architectures based on two formal properties: space complexity, which measures the RNN's memory, and rational recurrence, defined as whether the recurrent update can be described by a weighted finite-state machine. Expand

We extract syntactic trees from the pushing behavior of stack RNNs trained on language modeling and classification objectives, demonstrating that stack Rnns do indeed infer linguistically relevant hierarchical structure. Expand

We train a diachronic long short-term memory (LSTM) part-of-speech tagger on a large corpus of American English from the 19th, 20th, and 21st centuries. Expand