1 |
First the worst: Finding better gender translations during beam search ...
|
|
|
|
Abstract:
Generating machine translations via beam search seeks the most likely output under a model. However, beam search has been shown to amplify demographic biases exhibited by a model. We aim to address this, focusing on gender bias resulting from systematic errors in grammatical gender translation. Almost all prior work on this problem adjusts the training data or the model itself. By contrast, our ap- proach changes only the inference procedure. We explore two techniques: constraining beam search to improve gender diversity in n-best lists, and reranking n-best lists using gender features obtained from the source sentence. Combining these strongly improves WinoMT gender translation accuracy for three language pairs without additional bilingual data or re- training. We also demonstrate our approach’s utility for consistently gendering named enti- ties, and its flexibility to handle new gendered language beyond the binary. ... : EPSRC grants EP/M508007/1 and EP/N509620/1 and performed using resources from the Cambridge Tier-2 system operated by the University of Cambridge Research Computing Service funded by EPSRC Tier-2 cap- ital grant EP/P020259/1. ...
|
|
URL: https://dx.doi.org/10.17863/cam.82514 https://www.repository.cam.ac.uk/handle/1810/335074
|
|
BASE
|
|
Hide details
|
|
2 |
USC-SFI MALACH Interviews and Transcripts English – Speech Recognition Edition
|
|
|
|
BASE
|
|
Show details
|
|
3 |
USC-SFI MALACH Interviews and Transcripts English – Speech Recognition Edition ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT
|
|
Saunders, Danielle; Stahlberg, Felix; De Gispert, Adrià. - : Association for Computational Linguistics, 2018. : https://aclanthology.info/volumes/proceedings-of-the-56th-annual-meeting-of-the-association-for-computational-linguistics-volume-2-short-papers, 2018. : Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2018
|
|
BASE
|
|
Show details
|
|
5 |
Neural Machine Translation Decoding with Terminology Constraints
|
|
Hasler, eva; de Gspert, Adrià; Iglesias, Gonzalo. - : Association for Computational Linguistics, 2018. : https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-2018-conference-of-the-north-american-chapter-of-the-association-for-computational-linguistics-human-language-technologies-volume-2-short-papers, 2018
|
|
BASE
|
|
Show details
|
|
6 |
SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Unfolding and Shrinking Neural Machine Translation Ensembles
|
|
|
|
BASE
|
|
Show details
|
|
8 |
The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Fast and accurate preordering for SMT using neural networks
|
|
De Gispert, A; Iglesias, G; Byrne, William. - : Association for Computational Linguistics, 2015. : NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 2015
|
|
BASE
|
|
Show details
|
|
10 |
Hierarchical statistical semantic realization for minimal recursion semantics
|
|
Horvat, M; Copestake, Ann; Byrne, William. - : The Association for Computer Linguistics, 2015. : https://aclanthology.org/volumes/W15-01/, 2015. : IWCS 2015 - Proceedings of the 11th International Conference on Computational Semantics, 2015
|
|
BASE
|
|
Show details
|
|
11 |
The Geometry of Statistical Machine Translation
|
|
Waite, Aurelian; Byrne, William. - : ACL, 2015. : Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2015
|
|
BASE
|
|
Show details
|
|
|
|