Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks ACL

Suchin Gururangan | Ana Marasović | Swabha Swayamdipta | Kyle Lo | Iz Beltagy | Doug Downey | Noah A. Smith |

SPECTER: Document-level Representation Learning using Citation-informed Transformers ACL

Arman Cohan | Sergey Feldman | Iz Beltagy | Doug Downey | Daniel Weld |

Stolen Probability: A Structural Weakness of Neural Language Models ACL

David Demeter | Gregory Kimmel | Doug Downey |

Generative Data Augmentation for Commonsense Reasoning EMNLP Findings

Yiben Yang | Chaitanya Malaviya | Jared Fernandez | Swabha Swayamdipta | Ronan Le Bras | Ji-Ping Wang | Chandra Bhagavatula | Yejin Choi | Doug Downey |

Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models NAACL

Yiben Yang | Ji-Ping Wang | Doug Downey |

A Semantic Cover Approach for Topic Modeling *SEMEVAL

Rajagopal Venkatesaramani | Doug Downey | Bradley Malin | Yevgeniy Vorobeychik |

CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense NAACL WS

Michael Chen | Mike D’Arcy | Alisa Liu | Jared Fernandez | Doug Downey |

Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models EMNLP

Thanapon Noraset | Doug Downey | Lidong Bing |

Construction of the Literature Graph in Semantic Scholar NAACL

Waleed Ammar | Dirk Groeneveld | Chandra Bhagavatula | Iz Beltagy | Miles Crawford | Doug Downey | Jason Dunkelberger | Ahmed Elgohary | Sergey Feldman | Vu Ha | Rodney Kinney | Sebastian Kohlmeier | Kyle Lo | Tyler Murray | Hsu-Han Ooi | Matthew Peters | Joanna Power | Sam Skjonsberg | Lucy Wang | Chris Wilhelm | Zheng Yuan | Madeleine van Zuylen | Oren Etzioni |

Extracting Commonsense Properties from Embeddings with Limited Human Guidance ACL

Yiben Yang | Larry Birnbaum | Ji-Ping Wang | Doug Downey |

Sampling Informative Training Data for RNN Language Models ACL

Jared Fernandez | Doug Downey |

VecShare: A Framework for Sharing Word Representation Vectors EMNLP

Jared Fernandez | Zhaocheng Yu | Doug Downey |

Efficient Methods for Incorporating Knowledge into Topic Models EMNLP

Yi Yang | Doug Downey | Jordan Boyd-Graber |

Efficient Methods for Inferring Large Sparse Topic Hierarchies ACL IJCNLP

Doug Downey | Chandra Bhagavatula | Yi Yang |

Adding High-Precision Links to Wikipedia EMNLP

Thanapon Noraset | Chandra Bhagavatula | Doug Downey |

Learning Representations for Weakly Supervised Natural Language Processing Tasks CL

Fei Huang | Arun Ahuja | Doug Downey | Yi Yang | Yuhong Guo | Alexander Yates |

Active Learning with Constrained Topic Model WS

Yi Yang | Shimei Pan | Doug Downey | Kunpeng Zhang |

Overcoming the Memory Bottleneck in Distributed Training of Latent Variable Models of Text NAACL

Yi Yang | Alexander Yates | Doug Downey |

Scaling Semi-supervised Naive Bayes with Feature Marginals ACL

Michael Lucas | Doug Downey |

Local and Global Algorithms for Disambiguation to Wikipedia ACL

Lev Ratinov | Dan Roth | Doug Downey | Mike Anderson |

Language Models as Representations for Weakly Supervised NLP Tasks CoNLL WS

Fei Huang | Alexander Yates | Arun Ahuja | Doug Downey |

Improved Extraction Assessment through Better Language Models NAACL

Arun Ahuja | Doug Downey |

It’s a Contradiction – no, it’s not: A Case Study using Functional Relations EMNLP

Alan Ritter | Stephen Soderland | Doug Downey | Oren Etzioni |

Sparse Information Extraction: Unsupervised Language Models to the Rescue ACL

Doug Downey | Stefan Schoenmackers | Oren Etzioni |

KnowItNow: Fast, Scalable Information Extraction from the Web EMNLP HLT

Michael J. Cafarella | Doug Downey | Stephen Soderland | Oren Etzioni |