Competency Problems: On Finding and Removing Artifacts in Language Data EMNLP

Matt Gardner | William Merrill | Jesse Dodge | Matthew Peters | Alexis Ross | Sameer Singh | Noah A. Smith |

Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent EMNLP

William Merrill | Vivek Ramanujan | Yoav Goldberg | Roy Schwartz | Noah A. Smith |

Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? TACL

William Merrill | Yoav Goldberg | Roy Schwartz | Noah A. Smith |

A Formal Hierarchy of RNN Architectures ACL

William Merrill | Gail Weiss | Yoav Goldberg | Roy Schwartz | Noah A. Smith | Eran Yahav |

Sequential Neural Networks as Automata ACL WS

William Merrill |

Detecting Syntactic Change Using a Neural Part-of-Speech Tagger ACL WS

William Merrill | Gigi Stark | Robert Frank |

Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing ACL WS

William Merrill | Lenny Khazan | Noah Amsel | Yiding Hao | Simon Mendelsohn | Robert Frank |

End-to-End Graph-Based TAG Parsing with Neural Networks NAACL

Jungo Kasai | Robert Frank | Pauli Xu | William Merrill | Owen Rambow |

Context-Free Transductions with Neural Stacks EMNLP WS

Yiding Hao | William Merrill | Dana Angluin | Robert Frank | Noah Amsel | Andrew Benz | Simon Mendelsohn |