Coactive Learning for Interactive Machine Translation

Artem Sokolov, Stefan Riezler, Shay B. Cohen
; Proceedings of The 4th Workshop on Machine Learning for Interactive Systems at ICML 2015, PMLR 43:41-45, 2015.

Abstract

Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalization bounds for online learning with a feedback-based latent perceptron. We show experimentally that learning from weak feedback in machine translation leads to convergence in regret and translation error.

Cite this Paper


BibTeX
@InProceedings{pmlr-v43-sokolov15, title = {Coactive Learning for Interactive Machine Translation}, author = {Artem Sokolov and Stefan Riezler and Shay B. Cohen}, booktitle = {Proceedings of The 4th Workshop on Machine Learning for Interactive Systems at ICML 2015}, pages = {41--45}, year = {2015}, editor = {Heriberto Cuayáhuitl and Nina Dethlefs and Lutz Frommberger and Martijn Van Otterlo and Olivier Pietquin}, volume = {43}, series = {Proceedings of Machine Learning Research}, address = {Lille, France}, month = {11 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v43/sokolov15.pdf}, url = {http://proceedings.mlr.press/v43/sokolov15.html}, abstract = {Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalization bounds for online learning with a feedback-based latent perceptron. We show experimentally that learning from weak feedback in machine translation leads to convergence in regret and translation error.} }
Endnote
%0 Conference Paper %T Coactive Learning for Interactive Machine Translation %A Artem Sokolov %A Stefan Riezler %A Shay B. Cohen %B Proceedings of The 4th Workshop on Machine Learning for Interactive Systems at ICML 2015 %C Proceedings of Machine Learning Research %D 2015 %E Heriberto Cuayáhuitl %E Nina Dethlefs %E Lutz Frommberger %E Martijn Van Otterlo %E Olivier Pietquin %F pmlr-v43-sokolov15 %I PMLR %J Proceedings of Machine Learning Research %P 41--45 %U http://proceedings.mlr.press %V 43 %W PMLR %X Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalization bounds for online learning with a feedback-based latent perceptron. We show experimentally that learning from weak feedback in machine translation leads to convergence in regret and translation error.
RIS
TY - CPAPER TI - Coactive Learning for Interactive Machine Translation AU - Artem Sokolov AU - Stefan Riezler AU - Shay B. Cohen BT - Proceedings of The 4th Workshop on Machine Learning for Interactive Systems at ICML 2015 PY - 2015/06/18 DA - 2015/06/18 ED - Heriberto Cuayáhuitl ED - Nina Dethlefs ED - Lutz Frommberger ED - Martijn Van Otterlo ED - Olivier Pietquin ID - pmlr-v43-sokolov15 PB - PMLR SP - 41 DP - PMLR EP - 45 L1 - http://proceedings.mlr.press/v43/sokolov15.pdf UR - http://proceedings.mlr.press/v43/sokolov15.html AB - Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalization bounds for online learning with a feedback-based latent perceptron. We show experimentally that learning from weak feedback in machine translation leads to convergence in regret and translation error. ER -
APA
Sokolov, A., Riezler, S. & Cohen, S.B.. (2015). Coactive Learning for Interactive Machine Translation. Proceedings of The 4th Workshop on Machine Learning for Interactive Systems at ICML 2015, in PMLR 43:41-45

Related Material