Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Kevin Knight

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining


Feb 08, 2021
Boliang Zhang, Ying Lyu, Ning Ding, Tianhao Shen, Zhaoyang Jia, Kun Han, Kevin Knight


  Access Paper or Ask Questions

Why Neural Machine Translation Prefers Empty Outputs


Dec 24, 2020
Xing Shi, Yijun Xiao, Kevin Knight

* 6 pages 

  Access Paper or Ask Questions

MUSE: Illustrating Textual Attributes by Portrait Generation


Nov 09, 2020
Xiaodan Hu, Pengfei Yu, Kevin Knight, Heng Ji, Bo Li, Honghui Shi


  Access Paper or Ask Questions

DiDi's Machine Translation System for WMT2020


Oct 16, 2020
Tanfang Chen, Weiwei Wang, Wenyang Wei, Xing Shi, Xiangang Li, Jieping Ye, Kevin Knight

* Accepted at WMT 2020 

  Access Paper or Ask Questions

ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis


Oct 13, 2020
Qingyun Wang, Qi Zeng, Lifu Huang, Kevin Knight, Heng Ji, Nazneen Fatema Rajani

* 11 pages. Accepted by INLG 2020 

  Access Paper or Ask Questions

MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training


Oct 09, 2020
Arkady Arkhangorodsky, Amittai Axelrod, Christopher Chu, Scot Fang, Yiqi Huang, Ajay Nagesh, Xing Shi, Boliang Zhang, Kevin Knight

* 10 pages 

  Access Paper or Ask Questions

Solving Historical Dictionary Codes with a Neural Language Model


Oct 09, 2020
Christopher Chu, Raphael Valenti, Kevin Knight

* 10 pages, 6 figures. To appear in EMNLP 2020 

  Access Paper or Ask Questions

Learning to Pronounce Chinese Without a Pronunciation Dictionary


Oct 09, 2020
Christopher Chu, Scot Fang, Kevin Knight

* 7 pages. To appear in EMNLP 2020 

  Access Paper or Ask Questions

Parallel Corpus Filtering via Pre-trained Language Models


May 13, 2020
Boliang Zhang, Ajay Nagesh, Kevin Knight

* ACL 2020 

  Access Paper or Ask Questions

Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation


Jun 11, 2019
Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight, Jonathan May

* Accepted in ACL 2019 

  Access Paper or Ask Questions

PaperRobot: Incremental Draft Generation of Scientific Ideas


May 31, 2019
Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan

* 12 pages. Accepted by ACL 2019 Code and resource is available at https://github.com/EagleW/PaperRobot 

  Access Paper or Ask Questions

Plan-And-Write: Towards Better Automatic Storytelling


Nov 20, 2018
Lili Yao, Nanyun Peng, Ralph Weischedel, Kevin Knight, Dongyan Zhao, Rui Yan

* Accepted by AAAI 2019 

  Access Paper or Ask Questions

Decipherment of Historical Manuscript Images


Oct 09, 2018
Xusen Yin, Nada Aldarrab, Beáta Megyesi, Kevin Knight

* 10 pages 

  Access Paper or Ask Questions

Describing a Knowledge Base


Sep 30, 2018
Qingyun Wang, Xiaoman Pan, Lifu Huang, Boliang Zhang, Zhiying Jiang, Heng Ji, Kevin Knight

* 12 pages. Accepted by The 11th International Conference on Natural Language Generation (INLG 2018) Code at https://github.com/EagleW/Describing_a_Knowledge_Base 

  Access Paper or Ask Questions

Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words


Aug 16, 2018
Nelson F. Liu, Jonathan May, Michael Pust, Kevin Knight

* 7 pages 

  Access Paper or Ask Questions

Fast Locality Sensitive Hashing for Beam Search on GPU


Jun 02, 2018
Xing Shi, Shizhen Xu, Kevin Knight


  Access Paper or Ask Questions

Modeling Naive Psychology of Characters in Simple Commonsense Stories


May 16, 2018
Hannah Rashkin, Antoine Bosselut, Maarten Sap, Kevin Knight, Yejin Choi

* Accepted to ACL 2018 (long paper) 

  Access Paper or Ask Questions

Paper Abstract Writing through Editing Mechanism


May 15, 2018
Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight

* * Equal contribution. 6 pages. Accepted by ACL 2018; The code and dataset are available at https://github.com/EagleW/Writing-editing-Network 

  Access Paper or Ask Questions

Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding


Apr 21, 2018
Lifu Huang, Kyunghyun Cho, Boliang Zhang, Heng Ji, Kevin Knight

* 10 pages 

  Access Paper or Ask Questions

Recurrent Neural Networks as Weighted Language Recognizers


Mar 04, 2018
Yining Chen, Sorcha Gilroy, Andreas Maletti, Jonathan May, Kevin Knight


  Access Paper or Ask Questions

Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling


Feb 07, 2018
Prashanth Gurunath Shivakumar, Haoqi Li, Kevin Knight, Panayiotis Georgiou


  Access Paper or Ask Questions

Unsupervised Neural Hidden Markov Models


Sep 28, 2016
Ke Tran, Yonatan Bisk, Ashish Vaswani, Daniel Marcu, Kevin Knight

* accepted at EMNLP 2016, Workshop on Structured Prediction for NLP. Oral presentation 

  Access Paper or Ask Questions

Transfer Learning for Low-Resource Neural Machine Translation


Apr 08, 2016
Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight

* 8 pages 

  Access Paper or Ask Questions

Multi-Source Neural Translation


Jan 05, 2016
Barret Zoph, Kevin Knight

* 5 pages, 6 figures 

  Access Paper or Ask Questions

Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation


Apr 28, 2015
Michael Pust, Ulf Hermjakob, Kevin Knight, Daniel Marcu, Jonathan May

* 10 pages, 8 figures 

  Access Paper or Ask Questions

Empirical Methods for Compound Splitting


Feb 22, 2003
Philipp Koehn, Kevin Knight

* 8 pages, 2 figures. Published at EACL 2003 

  Access Paper or Ask Questions

Machine Transliteration


Apr 14, 1997
Kevin Knight, Jonathan Graehl

* 8 pages, postscript, to appear, ACL-97/EACL-97 

  Access Paper or Ask Questions

Unification-Based Glossing


Jun 10, 1995
Vasileios Hatzivassiloglou, Kevin Knight

* 8 pages, Compressed and uuencoded postscript. To appear: IJCAI-95 

  Access Paper or Ask Questions

Two-level, Many-Paths Generation


Jun 10, 1995
Kevin Knight, Vasileios Hatzivassiloglou

* 9 pages, Compressed and uuencoded postscript. To appear: ACL-95 

  Access Paper or Ask Questions