Filters








573 Hits in 4.6 sec

Neural Machine Translation for Cross-Lingual Pronoun Prediction

Sébastien Jean, Stanislas Lauly, Orhan Firat, Kyunghyun Cho
2017 Proceedings of the Third Workshop on Discourse in Machine Translation  
In this paper we present our systems for the DiscoMT 2017 cross-lingual pronoun prediction shared task.  ...  For all four language pairs, we trained a standard attention-based neural machine translation system as well as three variants that incorporate information from the preceding source sentence.  ...  Acknowledgments This work was supported by Samsung Electronics ("Larger-Context Neural Machine Translation" and "Next Generation Deep Learning: from pattern recognition to AI").  ... 
doi:10.18653/v1/w17-4806 dblp:conf/discomt/JeanLFC17 fatcat:vr4aci5vr5hcvmo54witfr3kxa

Does Neural Machine Translation Benefit from Larger Context? [article]

Sebastien Jean, Stanislas Lauly, Orhan Firat, Kyunghyun Cho
2017 arXiv   pre-print
We also discover that attention-based neural machine translation is well suited for pronoun prediction and compares favorably with other approaches that were specifically designed for this task.  ...  We propose a neural machine translation architecture that models the surrounding text in addition to the source sentence.  ...  Acknowledgments This work was supported by Samsung Electronics (Larger-Context Neural Machine Translation).  ... 
arXiv:1704.05135v1 fatcat:hwffguhl2vcqdlrvh6km53lzru

Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation [article]

Kellie Webster, Emily Pitler
2020 arXiv   pre-print
feminine pronouns, compared with 30-51% for neural machine translation models and 54-71% for a non-fine-tuned BERT model.  ...  We augment a neural machine translation model with labels from our classifier to improve pronoun translation, while still having parallelizable translation models that translate a sentence at a time.  ...  Acknowledgements We would like to thank Melvin Johnson, Romina Stella, and Macduff Hughes for assistance with machine translation work, as well as Mike Collins, Slav Petrov, and other members of the Google  ... 
arXiv:2006.08881v1 fatcat:kzxn4dmmsnfmbfx4kvlppc676q

Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Jimmy Callin, Christian Hardmeier, Jörg Tiedemann
2015 Proceedings of the Second Workshop on Discourse in Machine Translation  
For crosslingual pronoun prediction, we suggest a neural network-based model using preceding nouns and determiners as features for suggesting antecedent candidates.  ...  This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders.  ...  Task setup The goal of cross-lingual pronoun prediction is to accurately predict the correct missing pronoun in translated text.  ... 
doi:10.18653/v1/w15-2508 dblp:conf/discomt/CallinHT15 fatcat:2itcel4nfvbmxluqj2mvuguhde

Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction

Sharid Loáiciga, Sara Stymne, Preslav Nakov, Christian Hardmeier, Jörg Tiedemann, Mauro Cettolo, Yannick Versley
2017 Proceedings of the Third Workshop on Discourse in Machine Translation  
We describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction.  ...  The task asked participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence.  ...  Acknowledgements The organization of this task has received support from the following project: Discourse-Oriented Statistical Machine Translation funded by the Swedish Research Council (2012-916).  ... 
doi:10.18653/v1/w17-4801 dblp:conf/discomt/LoaicigaSNHTCV17 fatcat:sjwcdgwrlvaovp2nls5zeht73a

Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks

Juhani Luotolahti, Jenna Kanerva, Filip Ginter
2016 Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers  
In this paper we present our winning system in the WMT16 Shared Task on Cross-Lingual Pronoun Prediction, where the objective is to predict a missing target language pronoun based on the target and source  ...  Our system is a deep recurrent neural network, which reads both the source language and target language context with a softmax layer making the final prediction.  ...  Computational resources were provided by CSC -IT Center for Science.  ... 
doi:10.18653/v1/w16-2353 dblp:conf/wmt/LuotolahtiKG16 fatcat:ppknwqukwvdwdedwzbrn45cz54

Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks v2.0

Juhani Luotolahti, Jenna Kanerva, Filip Ginter
2017 Proceedings of the Third Workshop on Discourse in Machine Translation  
In this paper we present our system in the DiscoMT 2017 Shared Task on Crosslingual Pronoun Prediction.  ...  Our entry builds on our last year's success, our system based on deep recurrent neural networks outperformed all the other systems with a clear margin.  ...  Computational resources were provided by CSC -IT Center for Science, Finland.  ... 
doi:10.18653/v1/w17-4808 dblp:conf/discomt/LuotolahtiKG17 fatcat:bsxtg2g3gjhqdkvtrwwn4jgbqa

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Christian Hardmeier, Preslav Nakov, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo
2015 Proceedings of the Second Workshop on Discourse in Machine Translation  
(i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task  ...  Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task. 1 The example is taken from Hardmeier (2014, 92).  ...  Acknowledgements The manual evaluation of the pronoun-focused translation task was made possible thanks to a grant from the European Association for Machine Translation (EAMT).  ... 
doi:10.18653/v1/w15-2501 dblp:conf/discomt/HardmeierNSTVC15 fatcat:u3pws6ytcffu3k3a5ksiwex4x4

Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction

Liane Guillou, Christian Hardmeier, Preslav Nakov, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo, Bonnie Webber, Andrei Popescu-Belis
2016 Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers  
We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction.  ...  This is a classification task in which participants are asked to provide predictions on what pronoun class label should replace a placeholder value in the target-language text, provided in lemmatised and  ...  Conclusions We have described the design and the evaluation of the shared task on cross-lingual pronoun prediction at WMT 2016.  ... 
doi:10.18653/v1/w16-2345 dblp:conf/wmt/GuillouHNSTVCWP16 fatcat:yxwlmivwmrgzxd6j6mxfnnf6hy

Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction [article]

Liane Guillou, Christian Hardmeier, Preslav Nakov, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo, Bonnie Webber, Andrei Popescu-Belis
2019 arXiv   pre-print
We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction.  ...  This is a classification task in which participants are asked to provide predictions on what pronoun class label should replace a placeholder value in the target-language text, provided in lemmatised and  ...  Acknowledgements The organisation of this task has received support from the following project: Discourse-Oriented Statistical Machine Translation funded by the Swedish Research Council (2012-916) .  ... 
arXiv:1911.12091v1 fatcat:wavxuedwkreztansyhucy67exq

Predicting Pronouns with a Convolutional Network and an N-gram Model

Christian Hardmeier
2017 Proceedings of the Third Workshop on Discourse in Machine Translation  
This paper describes the UU-HARDMEIER system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction.  ...  The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.  ...  Overview For the 2017 cross-lingual pronoun prediction shared task, we chose to create a system that could be implemented very quickly while still providing an interesting comparison to the other systems  ... 
doi:10.18653/v1/w17-4807 dblp:conf/discomt/Hardmeier17 fatcat:bd4catudgbg2jk3y3owqfwmdla

Language Embeddings for Typology and Cross-lingual Transfer Learning [article]

Dian Yu and Taiqi He and Kenji Sagae
2021 arXiv   pre-print
Cross-lingual language tasks typically require a substantial amount of annotated data or parallel translation data.  ...  : cross-lingual dependency parsing and cross-lingual natural language inference.  ...  for cross-lingual tasks.  ... 
arXiv:2106.02082v1 fatcat:l4sdumpujvg2dbipbq4fz6pj5a

Dropped pronoun generation for dialogue machine translation

Longyue Wang, Xiaojun Zhang, Zhaopeng Tu, Hang Li, Qun Liu
2016 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In response to this problem, we propose a novel approach to improve the translation of DPs for dialogue machine translation.  ...  Dropped pronoun (DP) is a common problem in dialogue machine translation, in which pronouns are frequently dropped in the source sentence and thus are missing in its translation.  ...  Acknowledgments This research is supported by ADAPT Centre for Digital Content Technology funded under the SFI Research Centres Programme (Grant 13/RC/2106) and co-funded under the Euro-  ... 
doi:10.1109/icassp.2016.7472851 dblp:conf/icassp/WangZTLL16 fatcat:bs2uwupokrc6np2qktxlxvp7o4

A BiLSTM-based System for Cross-lingual Pronoun Prediction

Sara Stymne, Sharid Loáiciga, Fabienne Cap
2017 Proceedings of the Third Workshop on Discourse in Machine Translation  
We describe the Uppsala system for the 2017 DiscoMT shared task on crosslingual pronoun prediction.  ...  Classification is based on the BiLSTM representation of the source and target positions for the pronouns.  ...  SL was supported by the Swedish Research Council under project 2012-916 Discourse Oriented Statistical Machine Translation.  ... 
doi:10.18653/v1/w17-4805 dblp:conf/discomt/StymneLC17 fatcat:v6qlj4ytvfan5ke73qh6nqxzd4

Predicting Pronouns across Languages with Continuous Word Spaces

Ngoc-Quan Pham, Lonneke van der Plas
2015 Proceedings of the Second Workshop on Discourse in Machine Translation  
Predicting pronouns across languages from a language with less variation to one with much more is a hard task that requires many different types of information, such as morpho-syntactic information as  ...  Technologies (LCT) and the University of Malta and has been carried out using computational facilities procured through the European Regional Development Fund, Project ERDF-080 'A Supercomputing Laboratory for  ...  For the task of cross-lingual pronoun prediction, Hardmeier et al. (2013) also chose to learn the projection matrices and the neural network weights at the same 1.  ... 
doi:10.18653/v1/w15-2514 dblp:conf/discomt/PhamP15 fatcat:45krz25dj5caloo36g4og7xzfm
« Previous Showing results 1 — 15 out of 573 results