Christian Herold


2022

pdf
Detecting Various Types of Noise for Neural Machine Translation
Christian Herold | Jan Rosendahl | Joris Vanvinckenroye | Hermann Ney
Findings of the Association for Computational Linguistics: ACL 2022

The filtering and/or selection of training data is one of the core aspects to be considered when building a strong machine translation system.In their influential work, Khayrallah and Koehn (2018) investigated the impact of different types of noise on the performance of machine translation systems.In the same year the WMT introduced a shared task on parallel corpus filtering, which went on to be repeated in the following years, and resulted in many different filtering approaches being proposed.In this work we aim to combine the recent achievements in data filtering with the original analysis of Khayrallah and Koehn (2018) and investigate whether state-of-the-art filtering systems are capable of removing all the suggested noise types.We observe that most of these types of noise can be detected with an accuracy of over 90% by modern filtering systems when operating in a well studied high resource setting.However, we also find that when confronted with more refined noise categories or when working with a less common language pair, the performance of the filtering systems is far from optimal, showing that there is still room for improvement in this area of research.

pdf
Revisiting Checkpoint Averaging for Neural Machine Translation
Yingbo Gao | Christian Herold | Zijian Yang | Hermann Ney
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely adopted in neural machine translation research. Despite the popularity, the method itself simply takes the mean of the model parameters from several checkpoints, the selection of which is mostly based on empirical recipes without many justifications. In this work, we revisit the concept of checkpoint averaging and consider several extensions. Specifically, we experiment with ideas such as using different checkpoint selection strategies, calculating weighted average instead of simple mean, making use of gradient information and fine-tuning the interpolation weights on development data. Our results confirm the necessity of applying checkpoint averaging for optimal performance, but also suggest that the landscape between the converged checkpoints is rather flat and not much further improvement compared to simple averaging is to be obtained.

pdf
Is Encoder-Decoder Redundant for Neural Machine Translation?
Yingbo Gao | Christian Herold | Zijian Yang | Hermann Ney
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction and development of attention mechanism, encoder-decoder is still the de facto neural network architecture for state-of-the-art models. While the motivation for decoding information from some hidden space is straightforward, the strict separation of the encoding and decoding steps into an encoder and a decoder in the model architecture is not necessarily a must. Compared to the task of autoregressive language modeling in the target language, machine translation simply has an additional source sentence as context. Given the fact that neural language models nowadays can already handle rather long contexts in the target language, it is natural to ask whether simply concatenating the source and target sentences and training a language model to do translation would work. In this work, we investigate the aforementioned concept for machine translation. Specifically, we experiment with bilingual translation, translation with additional target monolingual data, and multilingual translation. In all cases, this alternative approach performs on par with the baseline encoder-decoder Transformer, suggesting that an encoder-decoder architecture might be redundant for neural machine translation.

pdf
Does Joint Training Really Help Cascaded Speech Translation?
Viet Anh Khoa Tran | David Thulke | Yingbo Gao | Christian Herold | Hermann Ney
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.However, fundamental challenges such as error propagation from the automatic speech recognition system still remain.To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods.In this work, we seek to answer the question of whether joint training really helps cascaded speech translation.We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities.Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training.We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation.

pdf
Locality-Sensitive Hashing for Long Context Neural Machine Translation
Frithjof Petrick | Jan Rosendahl | Christian Herold | Hermann Ney
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

After its introduction the Transformer architecture quickly became the gold standard for the task of neural machine translation. A major advantage of the Transformer compared to previous architectures is the faster training speed achieved by complete parallelization across timesteps due to the use of attention over recurrent layers. However, this also leads to one of the biggest problems of the Transformer, namely the quadratic time and memory complexity with respect to the input length. In this work we adapt the locality-sensitive hashing approach of Kitaev et al. (2020) to self-attention in the Transformer, we extended it to cross-attention and apply this memory efficient framework to sentence- and document-level machine translation. Our experiments show that the LSH attention scheme for sentence-level comes at the cost of slightly reduced translation quality. For document-level NMT we are able to include much bigger context sizes than what is possible with the baseline Transformer. However, more context does neither improve translation quality nor improve scores on targeted test suites.

2021

pdf
Recurrent Attention for the Transformer
Jan Rosendahl | Christian Herold | Frithjof Petrick | Hermann Ney
Proceedings of the Second Workshop on Insights from Negative Results in NLP

In this work, we conduct a comprehensive investigation on one of the centerpieces of modern machine translation systems: the encoder-decoder attention mechanism. Motivated by the concept of first-order alignments, we extend the (cross-)attention mechanism by a recurrent connection, allowing direct access to previous attention/alignment decisions. We propose several ways to include such a recurrency into the attention mechanism. Verifying their performance across different translation tasks we conclude that these extensions and dependencies are not beneficial for the translation performance of the Transformer architecture.

pdf
Data Filtering using Cross-Lingual Word Embeddings
Christian Herold | Jan Rosendahl | Joris Vanvinckenroye | Hermann Ney
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Data filtering for machine translation (MT) describes the task of selecting a subset of a given, possibly noisy corpus with the aim to maximize the performance of an MT system trained on this selected data. Over the years, many different filtering approaches have been proposed. However, varying task definitions and data conditions make it difficult to draw a meaningful comparison. In the present work, we aim for a more systematic approach to the task at hand. First, we analyze the performance of language identification, a tool commonly used for data filtering in the MT community and identify specific weaknesses. Based on our findings, we then propose several novel methods for data filtering, based on cross-lingual word embeddings. We compare our approaches to one of the winning methods from the WMT 2018 shared task on parallel corpus filtering on three real-life, high resource MT tasks. We find that said method, which was performing very strong in the WMT shared task, does not perform well within our more realistic task conditions. While we find that our approaches come out at the top on all three tasks, different variants perform best on different tasks. Further experiments on the WMT 2020 shared task for parallel corpus filtering show that our methods achieve comparable results to the strongest submissions of this campaign.

2020

pdf
Flexible Customization of a Single Neural Machine Translation System with Multi-dimensional Metadata Inputs
Evgeny Matusov | Patrick Wilken | Christian Herold
Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 2: User Track)

pdf
Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University
Parnia Bahar | Patrick Wilken | Tamer Alkhouli | Andreas Guta | Pavel Golik | Evgeny Matusov | Christian Herold
Proceedings of the 17th International Conference on Spoken Language Translation

AppTek and RWTH Aachen University team together to participate in the offline and simultaneous speech translation tracks of IWSLT 2020. For the offline task, we create both cascaded and end-to-end speech translation systems, paying attention to careful data selection and weighting. In the cascaded approach, we combine high-quality hybrid automatic speech recognition (ASR) with the Transformer-based neural machine translation (NMT). Our end-to-end direct speech translation systems benefit from pretraining of adapted encoder and decoder components, as well as synthetic data and fine-tuning and thus are able to compete with cascaded systems in terms of MT quality. For simultaneous translation, we utilize a novel architecture that makes dynamic decisions, learned from parallel data, to determine when to continue feeding on input or generate output words. Experiments with speech and text input show that even at low latency this architecture leads to superior translation results.

pdf
Diving Deep into Context-Aware Neural Machine Translation
Jingjing Huo | Christian Herold | Yingbo Gao | Leonard Dahlmann | Shahram Khadivi | Hermann Ney
Proceedings of the Fifth Conference on Machine Translation

Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various architectures and analyses, the effectiveness of different context-aware NMT models is not well explored yet. This paper analyzes the performance of document-level NMT models on four diverse domains with a varied amount of parallel document-level bilingual data. We conduct a comprehensive set of experiments to investigate the impact of document-level NMT. We find that there is no single best approach to document-level NMT, but rather that different architectures come out on top on different tasks. Looking at task-specific problems, such as pronoun resolution or headline translation, we find improvements in the context-aware systems, even in cases where the corpus-level metrics like BLEU show no significant improvement. We also show that document-level back-translation significantly helps to compensate for the lack of document-level bi-texts.

pdf
Towards a Better Understanding of Label Smoothing in Neural Machine Translation
Yingbo Gao | Weiyue Wang | Christian Herold | Zijian Yang | Hermann Ney
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

In order to combat overfitting and in pursuit of better generalization, label smoothing is widely applied in modern neural machine translation systems. The core idea is to penalize over-confident outputs and regularize the model so that its outputs do not diverge too much from some prior distribution. While training perplexity generally gets worse, label smoothing is found to consistently improve test performance. In this work, we aim to better understand label smoothing in the context of neural machine translation. Theoretically, we derive and explain exactly what label smoothing is optimizing for. Practically, we conduct extensive experiments by varying which tokens to smooth, tuning the probability mass to be deducted from the true targets and considering different prior distributions. We show that label smoothing is theoretically well-motivated, and by carefully choosing hyperparameters, the practical performance of strong neural machine translation systems can be further improved.

2019

pdf
The RWTH Aachen University Machine Translation Systems for WMT 2019
Jan Rosendahl | Christian Herold | Yunsu Kim | Miguel Graça | Weiyue Wang | Parnia Bahar | Yingbo Gao | Hermann Ney
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

This paper describes the neural machine translation systems developed at the RWTH Aachen University for the German-English, Chinese-English and Kazakh-English news translation tasks of the Fourth Conference on Machine Translation (WMT19). For all tasks, the final submitted system is based on the Transformer architecture. We focus on improving data filtering and fine-tuning as well as systematically evaluating interesting approaches like unigram language model segmentation and transfer learning. For the De-En task, none of the tested methods gave a significant improvement over last years winning system and we end up with the same performance, resulting in 39.6% BLEU on newstest2019. In the Zh-En task, we show 1.3% BLEU improvement over our last year’s submission, which we mostly attribute to the splitting of long sentences during translation. We further report results on the Kazakh-English task where we gain improvements of 11.1% BLEU over our baseline system. On the same task we present a recent transfer learning approach, which uses half of the free parameters of our submission system and performs on par with it.

pdf
Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification
Yingbo Gao | Christian Herold | Weiyue Wang | Hermann Ney
Proceedings of the 16th International Conference on Spoken Language Translation

Prominently used in support vector machines and logistic re-gressions, kernel functions (kernels) can implicitly map data points into high dimensional spaces and make it easier to learn complex decision boundaries. In this work, by replacing the inner product function in the softmax layer, we explore the use of kernels for contextual word classification. In order to compare the individual kernels, experiments are conducted on standard language modeling and machine translation tasks. We observe a wide range of performances across different kernel settings. Extending the results, we look at the gradient properties, investigate various mixture strategies and examine the disambiguation abilities.

2018

pdf
Improving Neural Language Models with Weight Norm Initialization and Regularization
Christian Herold | Yingbo Gao | Hermann Ney
Proceedings of the Third Conference on Machine Translation: Research Papers

Embedding and projection matrices are commonly used in neural language models (NLM) as well as in other sequence processing networks that operate on large vocabularies. We examine such matrices in fine-tuned language models and observe that a NLM learns word vectors whose norms are related to the word frequencies. We show that by initializing the weight norms with scaled log word counts, together with other techniques, lower perplexities can be obtained in early epochs of training. We also introduce a weight norm regularization loss term, whose hyperparameters are tuned via a grid search. With this method, we are able to significantly improve perplexities on two word-level language modeling tasks (without dynamic evaluation): from 54.44 to 53.16 on Penn Treebank (PTB) and from 61.45 to 60.13 on WikiText-2 (WT2).