Felix Hieber


2020

pdf bib
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
Tobias Domhan | Michael Denkowski | David Vilar | Xing Niu | Felix Hieber | Kenneth Heafield
Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

pdf bib
Sockeye 2: A Toolkit for Neural Machine Translation
Felix Hieber | Tobias Domhan | Michael Denkowski | David Vilar
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation

We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet’s Gluon API, a focus on state of the art model architectures, and distributed mixed precision training. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.

2018

pdf bib
The Sockeye Neural Machine Translation Toolkit at AMTA 2018
Felix Hieber | Tobias Domhan | Michael Denkowski | David Vilar | Artem Sokolov | Ann Clifton | Matt Post
Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

2017

pdf bib
Using Target-side Monolingual Data for Neural Machine Translation through Multi-task Learning
Tobias Domhan | Felix Hieber
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

The performance of Neural Machine Translation (NMT) models relies heavily on the availability of sufficient amounts of parallel data, and an efficient and effective way of leveraging the vastly available amounts of monolingual data has yet to be found. We propose to modify the decoder in a neural sequence-to-sequence model to enable multi-task learning for two strongly related tasks: target-side language modeling and translation. The decoder predicts the next target word through two channels, a target-side language model on the lowest layer, and an attentional recurrent model which is conditioned on the source representation. This architecture allows joint training on both large amounts of monolingual and moderate amounts of bilingual data to improve NMT performance. Initial results in the news domain for three language pairs show moderate but consistent improvements over a baseline trained on bilingual data only.

2015

pdf bib
Bag-of-Words Forced Decoding for Cross-Lingual Information Retrieval
Felix Hieber | Stefan Riezler
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2014

pdf bib
Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval
Shigehiko Schamoni | Felix Hieber | Artem Sokolov | Stefan Riezler
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2013

pdf bib
Boosting Cross-Language Retrieval by Learning Bilingual Phrase Associations from Relevance Rankings
Artem Sokokov | Laura Jehl | Felix Hieber | Stefan Riezler
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Task Alternation in Parallel Sentence Retrieval for Twitter Translation
Felix Hieber | Laura Jehl | Stefan Riezler
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
Twitter Translation using Translation-Based Cross-Lingual Retrieval
Laura Jehl | Felix Hieber | Stefan Riezler
Proceedings of the Seventh Workshop on Statistical Machine Translation

2010

pdf bib
Generating LTAG grammars from a lexicon/ontology interface
Christina Unger | Felix Hieber | Philipp Cimiano
Proceedings of the 10th International Workshop on Tree Adjoining Grammar and Related Frameworks (TAG+10)