How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVEN TACL

R. Thomas McCoy | Paul Smolensky | Tal Linzen | Jianfeng Gao | Asli Celikyilmaz |

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization NAACL

Yichen Jiang | Asli Celikyilmaz | Paul Smolensky | Paul Soulos | Sudha Rao | Hamid Palangi | Roland Fernandez | Caitlin Smith | Mohit Bansal | Jianfeng Gao |

Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages MTSummit

Paul Soulos | Sudha Rao | Caitlin Smith | Eric Rosen | Asli Celikyilmaz | R. Thomas McCoy | Yichen Jiang | Coleman Haley | Roland Fernandez | Hamid Palangi | Jianfeng Gao | Paul Smolensky |

Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme COLING

Coleman Haley | Paul Smolensky |

Discovering the Compositional Structure of Vector Representations with Role Learning Networks BlackboxNLP EMNLP

Paul Soulos | R. Thomas McCoy | Tal Linzen | Paul Smolensky |

Augmentic Compositional Models for Knowledge Base Completion Using Gradient Representations SCiL WS

Matthias R. Lalisse | Paul Smolensky |

Tensor Product Generation Networks for Deep NLP Modeling NAACL

Qiuyuan Huang | Paul Smolensky | Xiaodong He | Li Deng | Dapeng Wu |

Dynamic encoding of structural uncertainty in gradient symbols CMCL WS

Pyeong Whan Cho | Matthew Goldrick | Richard L. Lewis | Paul Smolensky |

Optimality Theory: Universal Grammar, Learning and Parsing Algorithms, and Connectionist Foundations (Abstract) ACL

Paul Smolensky | Bruce Tesar |