Daniel Stein


2017

pdf bib
Human Evaluation of Multi-modal Neural Machine Translation: A Case-Study on E-Commerce Listing Titles
Iacer Calixto | Daniel Stein | Evgeny Matusov | Sheila Castilho | Andy Way
Proceedings of the Sixth Workshop on Vision and Language

In this paper, we study how humans perceive the use of images as an additional knowledge source to machine-translate user-generated product listings in an e-commerce company. We conduct a human evaluation where we assess how a multi-modal neural machine translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attention-based NMT and a phrase-based statistical machine translation (PBSMT) model. We evaluate translations obtained with different systems and also discuss the data set of user-generated product listings, which in our case comprises both product listings and associated images. We found that humans preferred translations obtained with a PBSMT system to both text-only and multi-modal NMT over 56% of the time. Nonetheless, human evaluators ranked translations from a multi-modal NMT model as better than those of a text-only NMT over 88% of the time, which suggests that images do help NMT in this use-case.

pdf bib
Using Images to Improve Machine-Translating E-Commerce Product Listings.
Iacer Calixto | Daniel Stein | Evgeny Matusov | Pintu Lohar | Sheila Castilho | Andy Way
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

In this paper we study the impact of using images to machine-translate user-generated e-commerce product listings. We study how a multi-modal Neural Machine Translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attentional NMT and a Statistical Machine Translation (SMT) model. User-generated product listings often do not constitute grammatical or well-formed sentences. More often than not, they consist of the juxtaposition of short phrases or keywords. We train our models end-to-end as well as use text-only and multi-modal NMT models for re-ranking n-best lists generated by an SMT model. We qualitatively evaluate our user-generated training data also analyse how adding synthetic data impacts the results. We evaluate our models quantitatively using BLEU and TER and find that (i) additional synthetic data has a general positive impact on text-only and multi-modal NMT models, and that (ii) using a multi-modal NMT model for re-ranking n-best lists improves TER significantly across different n-best list sizes.

2014

pdf bib
Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System
Michael Stadtschnitzer | Jochen Schwenninger | Daniel Stein | Joachim Koehler
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

In this paper we describe the large-scale German broadcast corpus (GER-TV1000h) containing more than 1,000 hours of transcribed speech data. This corpus is unique in the German language corpora domain and enables significant progress in tuning the acoustic modelling of German large vocabulary continuous speech recognition (LVCSR) systems. The exploitation of this huge broadcast corpus is demonstrated by optimizing and improving the Fraunhofer IAIS speech recognition system. Due to the availability of huge amount of acoustic training data new training strategies are investigated. The performance of the automatic speech recognition (ASR) system is evaluated on several datasets and compared to previously published results. It can be shown that the word error rate (WER) using a larger corpus can be reduced by up to 9.1 % relative. By using both larger corpus and recent training paradigms the WER was reduced by up to 35.8 % relative and below 40 % absolute even for spontaneous dialectal speech in noisy conditions, making the ASR output a useful resource for subsequent tasks like named entity recognition also in difficult acoustic situations.

2012

pdf bib
Automatic Speech Recognition on a Firefighter TETRA Broadcast Channel
Daniel Stein | Bela Usabaev
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

For a reliable keyword extraction on firefighter radio communication, a strong automatic speech recognition system is needed. However, real-life data poses several challenges like a distorted voice signal, background noise and several different speakers. Moreover, the domain is out-of-scope for common language models, and the available data is scarce. In this paper, we introduce the PRONTO corpus, which consists of German firefighter exercise transcriptions. We show that by standard adaption techniques the recognition rate already rises from virtually zero to up to 51.7% and can be further improved by domain-specific rules to 47.9%. Extending the acoustic material by semi-automatic transcription and crawled in-domain written material, we arrive at a WER of 45.2%.

2011

pdf bib
Advancements in Arabic-to-English Hierarchical Machine Translation
Matthias Huck | David Vilar | Daniel Stein | Hermann Ney
Proceedings of the 15th Annual Conference of the European Association for Machine Translation

pdf bib
Soft string-to-dependency hierarchical machine translation
Jan-Thorsten Peter | Matthias Huck | Hermann Ney | Daniel Stein
Proceedings of the 8th International Workshop on Spoken Language Translation: Papers

In this paper, we dissect the influence of several target-side dependency-based extensions to hierarchical machine translation, including a dependency language model (LM). We pursue a non-restrictive approach that does not prohibit the production of hypotheses with malformed dependency structures. Since many questions remained open from previous and related work, we offer in-depth analysis of the influence of the language model order, the impact of dependency-based restrictions on the search space, and the information to be gained from dependency tree building during decoding. The application of a non-restrictive approach together with an integrated dependency LM scoring is a novel contribution which yields significant improvements for two large-scale translation tasks for the language pairs Chinese–English and German–French.

pdf bib
The RWTH Aachen Machine Translation System for WMT 2011
Matthias Huck | Joern Wuebker | Christoph Schmidt | Markus Freitag | Stephan Peitz | Daniel Stein | Arnaud Dagnelies | Saab Mansour | Gregor Leusch | Hermann Ney
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf bib
Lightly-Supervised Training for Hierarchical Phrase-Based Machine Translation
Matthias Huck | David Vilar | Daniel Stein | Hermann Ney
Proceedings of the First workshop on Unsupervised Learning in NLP

2010

pdf bib
The RWTH Aachen Machine Translation System for WMT 2010
Carmen Heger | Joern Wuebker | Matthias Huck | Gregor Leusch | Saab Mansour | Daniel Stein | Hermann Ney
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf bib
Jane: Open Source Hierarchical Translation, Extended with Reordering and Lexicon Models
David Vilar | Daniel Stein | Matthias Huck | Hermann Ney
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf bib
Sign language machine translation overkill
Daniel Stein | Christoph Schmidt | Hermann Ney
Proceedings of the 7th International Workshop on Spoken Language Translation: Papers

Sign languages represent an interesting niche for statistical machine translation that is typically hampered by the scarceness of suitable data, and most papers in this area apply only a few, well-known techniques and do not adapt them to small-sized corpora. In this paper, we will propose new methods for common approaches like scaling factor optimization and alignment merging strategies which helped improve our baseline. We also conduct experiments with different decoders and employ state-of-the-art techniques like soft syntactic labels as well as trigger-based and discriminative word lexica and system combination. All methods are evaluated on one of the largest sign language corpora available.

pdf bib
If I only had a parser: poor man’s syntax for hierarchical machine translation
David Vilar | Daniel Stein | Stephan Peitz | Hermann Ney
Proceedings of the 7th International Workshop on Spoken Language Translation: Papers

pdf bib
A Cocktail of Deep Syntactic Features for Hierarchical Machine Translation
Daniel Stein | Stephan Peitz | David Vilar | Hermann Ney
Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers

In this work we review and compare three additional syntactic enhancements for the hierarchical phrase-based translation model, which have been presented in the last few years. We compare their performance when applied separately and study whether the combination may yield additional improvements. Our findings show that the models are complementary, and their combination achieve an increase of 1% in BLEU and a reduction of nearly 2% in TER. The models presented in this work are made available as part of the Jane open source machine translation toolkit.

2009

pdf bib
The RWTH Machine Translation System for WMT 2009
Maja Popović | David Vilar | Daniel Stein | Evgeny Matusov | Hermann Ney
Proceedings of the Fourth Workshop on Statistical Machine Translation

2008

pdf bib
The RWTH machine translation system for IWSLT 2008.
David Vilar | Daniel Stein | Yuqi Zhang | Evgeny Matusov | Arne Mauser | Oliver Bender | Saab Mansour | Hermann Ney
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

RWTH’s system for the 2008 IWSLT evaluation consists of a combination of different phrase-based and hierarchical statistical machine translation systems. We participated in the translation tasks for the Chinese-to-English and Arabic-to-English language pairs. We investigated different preprocessing techniques, reordering methods for the phrase-based system, including reordering of speech lattices, and syntax-based enhancements for the hierarchical systems. We also tried the combination of the Arabic-to-English and Chinese-to-English outputs as an additional submission.

pdf bib
Analysing soft syntax features and heuristics for hierarchical phrase based machine translation.
David Vilar | Daniel Stein | Hermann Ney
Proceedings of the 5th International Workshop on Spoken Language Translation: Papers

Similar to phrase-based machine translation, hierarchical systems produce a large proportion of phrases, most of which are supposedly junk and useless for the actual translation. For the hierarchical case, however, the amount of extracted rules is an order of magnitude bigger. In this paper, we investigate several soft constraints in the extraction of hierarchical phrases and whether these help as additional scores in the decoding to prune unneeded phrases. We show the methods that help best.

pdf bib
The ATIS Sign Language Corpus
Jan Bungeroth | Daniel Stein | Philippe Dreuw | Hermann Ney | Sara Morrissey | Andy Way | Lynette van Zijl
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Systems that automatically process sign language rely on appropriate data. We therefore present the ATIS sign language corpus that is based on the domain of air travel information. It is available for five languages, English, German, Irish sign language, German sign language and South African sign language. The corpus can be used for different tasks like automatic statistical translation and automatic sign language recognition and it allows the specific modeling of spatial references in signing space.

2007

pdf bib
Combining data-driven MT systems for improved sign language translation
Sara Morrissey | Andy Way | Daniel Stein | Jan Bungeroth | Hermann Ney
Proceedings of Machine Translation Summit XI: Papers

pdf bib
Hand in hand: automatic sign language to English translation
Daniel Stein | Philippe Dreuw | Hermann Ney | Sara Morrissey | Andy Way
Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages: Papers

2006

pdf bib
A German Sign Language Corpus of the Domain Weather Report
Jan Bungeroth | Daniel Stein | Philippe Dreuw | Morteza Zahedi | Hermann Ney
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus. All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus.

pdf bib
Morpho-Syntax Based Statistical Methods for Automatic Sign Language Translation
Daniel Stein | Jan Bungeroth | Hermann Ney
Proceedings of the 11th Annual Conference of the European Association for Machine Translation