The Karlsruhe Institute of Technology Translation Systems for the WMT 2015

Cho, Eunah; Ha, Thanh-Le; Niehues, Jan; Herrmann, Thomas; Mediani, Mohammed; Zhang, Yuqi; Waibel, Alex

doi:10.18653/v1/w15-3008

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The incorporation of morphological information into the NMT model has been a challenging task in various studies. Additional linguistic information such as POS tags has been integrated for language models [22] , [23] . In neural machine translation, incorporating additional linguistic information is beneficial [16] .…”

Section: Related Workmentioning

confidence: 99%

Improving neural machine translation with POS-tag features for low-resource language pairs

Hlaing

Thu

Supnithi

et al. 2022

Heliyon

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Improving neural machine translation with POS-tag features for low-resource language pairs

Hlaing

Thu

Supnithi

et al. 2022

Heliyon

View full text Add to dashboard Cite

“…The system uses a pre-reordering technique and facilitates several translation and language models. A full system description can be found in (Cho et al, 2015). The German to English baseline system uses 19 features and the English to German systems uses 22 features.…”

Section: Systemsmentioning

confidence: 99%

ListNet-based MT Rescoring

Niehues

Do²,

Allauzen

et al. 2015

Proceedings of the Tenth Workshop on Statistical Machine Translation

Self Cite

View full text Add to dashboard Cite

The log-linear combination of different features is an important component of SMT systems. It allows for the easy integartion of models into the system and is used during decoding as well as for nbest list rescoring. With the recent success of more complex models like neural network-based translation models, n-best list rescoring attracts again more attention. In this work, we present a new technique to train the log-linear model based on the ListNet algorithm. This technique scales to many features, considers the whole list and not single entries during learning and can also be applied to more complex models than a log-linear combination. Using the new learning approach, we improve the translation quality of a largescale system by 0.8 BLEU points during rescoring and generate translations which are up to 0.3 BLEU points better than other learning techniques such as MERT or MIRA.

show abstract

“…The fundamental setup is loosely based on the system submitted by Cho et al (2013) to the WMT 2013 shared task. Our phrase table is trained on data taken from the News commentary, Europarl, UN, Common crawl and 10 9 corpora.…”

Section: English-frenchmentioning

confidence: 99%