Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation ACL

Vihan Jain | Gabriel Magalhaes | Alexander Ku | Ashish Vaswani | Eugene Ie | Jason Baldridge |

Self-Attention with Relative Position Representations NAACL

Peter Shaw | Jakob Uszkoreit | Ashish Vaswani |

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation ACL

Mia Xu Chen | Orhan Firat | Ankur Bapna | Melvin Johnson | Wolfgang Macherey | George Foster | Llion Jones | Mike Schuster | Noam Shazeer | Niki Parmar | Ashish Vaswani | Jakob Uszkoreit | Lukasz Kaiser | Zhifeng Chen | Yonghui Wu | Macduff Hughes |

Tensor2Tensor for Neural Machine Translation AMTA WS

Ashish Vaswani | Samy Bengio | Eugene Brevdo | Francois Chollet | Aidan Gomez | Stephan Gouws | Llion Jones | Łukasz Kaiser | Nal Kalchbrenner | Niki Parmar | Ryan Sepassi | Noam Shazeer | Jakob Uszkoreit |

Supertagging With LSTMs NAACL

Ashish Vaswani | Yonatan Bisk | Kenji Sagae | Ryan Musa |

Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning NAACL

Boliang Zhang | Xiaoman Pan | Tianlu Wang | Ashish Vaswani | Heng Ji | Kevin Knight | Daniel Marcu |

Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies NAACL

Barret Zoph | Ashish Vaswani | Jonathan May | Kevin Knight |

Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States TACL

Ashish Vaswani | Kenji Sagae |

Unsupervised Neural Hidden Markov Models WS

Ke M. Tran | Yonatan Bisk | Ashish Vaswani | Daniel Marcu | Kevin Knight |

Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data NAACL

Tomer Levinboim | Ashish Vaswani | David Chiang |

Unifying Bayesian Inference and Vector Space Models for Improved Decipherment ACL IJCNLP

Qing Dou | Ashish Vaswani | Kevin Knight | Chris Dyer |

Aligning context-based statistical models of language with brain activity during reading EMNLP

Leila Wehbe | Ashish Vaswani | Kevin Knight | Tom Mitchell |

Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation EMNLP

Qing Dou | Ashish Vaswani | Kevin Knight |

Decoding with Large-Scale Neural Language Models Improves Translation EMNLP

Ashish Vaswani | Yinggong Zhao | Victoria Fossum | David Chiang |

Learning Whom to Trust with MACE NAACL

Dirk Hovy | Taylor Berg-Kirkpatrick | Ashish Vaswani | Eduard Hovy |

Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm ACL

Ashish Vaswani | Liang Huang | David Chiang |

Rule Markov Models for Fast Tree-to-String Translation ACL

Ashish Vaswani | Haitao Mi | Liang Huang | David Chiang |

Models and Training for Unsupervised Preposition Sense Disambiguation ACL

Dirk Hovy | Ashish Vaswani | Stephen Tratz | David Chiang | Eduard Hovy |

Fast, Greedy Model Minimization for Unsupervised Tagging COLING

Sujith Ravi | Ashish Vaswani | Kevin Knight | David Chiang |

Efficient Optimization of an MDL-Inspired Objective Function for Unsupervised Part-Of-Speech Tagging ACL

Ashish Vaswani | Adam Pauls | David Chiang |

Hassan: A Virtual Human for Tactical Questioning SIGDIAL

David Traum | Antonio Roque | Anton Leuski | Panayiotis Georgiou | Jillian Gerten | Bilyana Martinovski | Shrikanth Narayanan | Susan Robinson | Ashish Vaswani |