v1v2 (latest)

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models

1 August 2017

Kartik Goyal

Graham Neubig

Chris Dyer

Taylor Berg-Kirkpatrick

3DV

ArXiv (abs)PDF HTML

Papers citing "A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models"

26 / 26 papers shown

Title
Beam Tree Recursive Cells Jishnu Ray Chowdhury Cornelia Caragea 91 6 0 31 May 2023
Learning to Summarize Videos by Contrasting Clips Ivan Sosnovik A. Moskalev Cees Kaandorp A. Smeulders 66 0 0 12 Jan 2023
Differentiable Top-k Classification Learning Felix Petersen Hilde Kuehne Christian Borgelt Oliver Deussen 135 32 0 15 Jun 2022
Monotonic Differentiable Sorting Networks Felix Petersen Christian Borgelt Hilde Kuehne Oliver Deussen 73 26 0 17 Mar 2022
Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP Lifu Tu BDL 64 0 0 27 Aug 2021
Incremental Beam Manipulation for Natural Language Generation J. Hargreaves Andreas Vlachos Guy Edward Toh Emerson 48 7 0 04 Feb 2021
An Empirical Investigation of Beam-Aware Training in Supertagging Renato M. P. Negrinho Matthew R. Gormley Geoffrey J. Gordon 83 3 0 10 Oct 2020
Successive Halving Top-k Operator Michal Pietruszka Łukasz Borchmann Filip Graliñski 36 6 0 08 Oct 2020
Text Generation by Learning from Demonstrations Richard Yuanzhe Pang He He OffRL 70 80 0 16 Sep 2020
Sparsifying Transformer Models with Trainable Representation Pooling Michal Pietruszka Łukasz Borchmann Lukasz Garncarek 91 12 0 10 Sep 2020
Learning Optimal Tree Models Under Beam Search Jingwei Zhuo Xinhang Li Wei Dai Ziru Xu Han Li Jian Xu Kun Gai 79 60 0 27 Jun 2020
Natural Language Processing Advancements By Deep Learning: A Survey A. Torfi Rouzbeh A. Shirvani Yaser Keneshloo Nader Tavvaf Edward A. Fox AI4CE VLM 161 222 0 02 Mar 2020
Differentiable Top-k Operator with Optimal Transport Yujia Xie H. Dai Minshuo Chen Bo Dai T. Zhao H. Zha Wei Wei Tomas Pfister OT 70 27 0 16 Feb 2020
Neural Machine Translation: A Review and Survey Felix Stahlberg 3DV AI4TS MedIm 142 332 0 04 Dec 2019
Deep Learning Based Chatbot Models Richard Csaky 74 46 0 23 Aug 2019
An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search Kartik Goyal Chris Dyer Taylor Berg-Kirkpatrick 63 16 0 15 Apr 2019
Benchmarking Approximate Inference Methods for Neural Structured Prediction Lifu Tu Kevin Gimpel BDL 93 17 0 01 Apr 2019
Stochastic Optimization of Sorting Networks via Continuous Relaxations Aditya Grover Eric Wang Aaron Zweig Stefano Ermon 101 174 0 21 Mar 2019
Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement W. Kool H. V. Hoof Max Welling 142 220 0 14 Mar 2019
A Fully Differentiable Beam Search Decoder R. Collobert Awni Y. Hannun Gabriel Synnaeve 86 40 0 16 Feb 2019
Value-based Search in Execution Space for Mapping Instructions to Programs Dor Muhlgay Jonathan Herzig Jonathan Berant 63 6 0 02 Nov 2018
Learning Beam Search Policies via Imitation Learning Renato M. P. Negrinho Matthew R. Gormley Geoffrey J. Gordon 118 27 0 01 Nov 2018
Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder Caio Corro Ivan Titov BDL 58 56 0 25 Jul 2018
Learning Approximate Inference Networks for Structured Prediction Lifu Tu Kevin Gimpel BDL 59 53 0 09 Mar 2018
Differentiable Dynamic Programming for Structured Prediction and Attention A. Mensch Mathieu Blondel 75 131 0 11 Feb 2018
Differentiable lower bound for expected BLEU score Vlad Zhukov Eugene Golikov M. Kretov 43 15 0 13 Dec 2017