Papers by Hermann Ney
Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition (D18-2)
Copied to clipboard
| Challenge: | Sisyphus is a workflow manager for Python that can be used for large and complicated workflows. |
| Approach: | Sisyphus is a Python-based workflow manager that can be used to train and test a machine . it maps all jobs to a unique path and can create links bearing descriptive names. |
| Outcome: | Sisyphus is a Python-based workflow manager that can handle large experiments . it can be used without modification to edit, debug, document the workflow . |
Is Encoder-Decoder Redundant for Neural Machine Translation? (2022.aacl-main)
Copied to clipboard
| Challenge: | Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. |
| Approach: | They propose to combine bilingual and multilingual translations to train a language model to do translation. |
| Outcome: | The proposed approach performs on par with the baseline encoder-decoder Transformer . the proposed approach is compared with the translation model in the target language . |
uniblock: Scoring and Filtering Corpus with Unicode Block Information (D19-1)
Copied to clipboard
| Challenge: | Existing methods to remove sentences consisting of illegal characters are tedious and repetitive. |
| Approach: | They propose a statistical method to identify illegal characters in natural language processing . they use a fixed-size feature vector to generate a Gaussian mixture model for each sentence . |
| Outcome: | The proposed method can score sentences and filter corpus on clean corpus and improve performance. |
Revisiting Checkpoint Averaging for Neural Machine Translation (2022.findings-aacl)
Copied to clipboard
| Challenge: | Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. |
| Approach: | They propose to use checkpoint averaging to increase model performance . they also propose to calculate weighted average instead of simple mean . |
| Outcome: | The proposed method is widely adopted in neural machine translation research. |
Neural Language Modeling for Named Entity Recognition (2020.coling-main)
Copied to clipboard
| Challenge: | Experimental results show that named entity recognition systems are faster and more flexible for the size of the corpus. |
| Approach: | They propose to use a neural language model as an alternative to the conditional random field layer for named entity recognition. |
| Outcome: | The proposed system has a significant speed advantage with a marginal performance degradation. |
Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies are limited to cognate languages. |
| Approach: | They propose to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies by using cross-lingual word embedding and injecting artificial noises. |
| Outcome: | The proposed methods outperform multilingual joint training by a large margin in five low-resource translation tasks. |
Detecting Various Types of Noise for Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | a recent study investigated the impact of noise on the performance of machine translation systems. |
| Approach: | They propose to combine recent research on data filtering with original analysis . they find that most of the suggested noise types can be detected with 90% accuracy . |
| Outcome: | The proposed filtering systems can detect noise types with 90% accuracy in high resource settings. |
Improving Language Model Integration for Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to integrate external language models into machine translation systems have been based on the assumption that the external model learns an implicit target-side language model at decoding time. |
| Approach: | They transfer this concept to the task of machine translation and compare it with the most prominent way of including additional monolingual data - namely back-translation. |
| Outcome: | The proposed approach outperforms the most prominent way of including additional monolingual data, namely back-translation. |
Towards a Better Understanding of Label Smoothing in Neural Machine Translation (2020.aacl-main)
Copied to clipboard
| Challenge: | In recent years, Neural Network (NN) models bring steady and concrete improvements on the task of Machine Translation (MT). |
| Approach: | They propose to penalize over-confident outputs and regularize the model so that its outputs do not diverge too much from some prior distribution. |
| Outcome: | The proposed method is well-motivated and can improve the performance of strong neural machine translation systems. |
Predicting and Using Target Length in Neural Machine Translation (2020.aacl-main)
Copied to clipboard
| Challenge: | Current NMT systems do not model the length of the output explicitly . length normalization is a common technique used in the beam search of NMT to enable a fair comparison of partial hypotheses with different lengths. |
| Approach: | They propose to use length prediction as an auxiliary task to obtain length information from the encoder. |
| Outcome: | The proposed sub-network improves over the baseline system and the predicted length can be used as an alternative to length normalization during decoding. |
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages (D19-1)
Copied to clipboard
| Challenge: | Using parallel corpora, we train a single, direct NMT model for non-English language pairs. |
| Approach: | They propose three ways to increase the relation among source, pivot, and target languages in pre-training . they use additional adapter component to smoothly connect pre-trained encoder and decoder . |
| Outcome: | The proposed methods outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. |
Investigation on Data Adaptation Techniques for Neural Named Entity Recognition (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition use only a limited number of samples . data augmentation and selftraining are popular methods to generate additional synthetic data . |
| Approach: | They investigate the impact of data augmentation and data augmented on named entity recognition tasks. |
| Outcome: | The proposed methods improve the performance of three named entity recognition tasks. |
Unifying Input and Output Smoothing in Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Recent methods that smooth input and output of neural machine translation systems bring significant improvements in performance. |
| Approach: | They propose a method that replaces one-hot representations with soft posterior distributions of an external language model, smoothing the input of machine translation systems. |
| Outcome: | The proposed method improves translation performance on small datasets and larger datasets. |
On Search Strategies for Document-Level Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Document-level neural machine translation models produce a more consistent output across a document . however, the exact decoding strategy is often not described and not mentioned at all. |
| Approach: | They propose to use standard automatic metrics and specific linguistic phenomena to compare different decoding schemes. |
| Outcome: | The proposed decoding strategies perform similar to each other on three standard document-level translation benchmarks. |
Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has achieved significant progress over recent years. |
| Approach: | They extend mutual learning to the machine translation task and operate at both the sentence-level and the token-level. |
| Outcome: | The proposed method improves on the IWSLT’14 German-English task and also on the WMT’14 English-German task. |
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition (P18-4)
Copied to clipboard
| Challenge: | Using RETURNN, we train and decode attention models for translation and speech recognition. |
| Approach: | They propose a layer-wise pretraining scheme for recurrent attention models and show its significant effect on deep recurrence encoder networks. |
| Outcome: | The proposed training and decoding scheme improves 1% on expected training and improves on WMT 2017 and Switchboard. |
Data Filtering using Cross-Lingual Word Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | varying task definitions and data conditions make it difficult to draw a meaningful comparison. |
| Approach: | They propose to use language identification to perform data filtering on MT data based on cross-lingual word embeddings to identify weaknesses in language identification tool. |
| Outcome: | The proposed methods perform well on three real-life, high resource MT tasks while performing weakly within more realistic task conditions. |
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale pre-trained MLMs can be used to generalize well to a wide range of tasks. |
| Approach: | They propose to append [MASK]s at a later layer to reduce sequence length for earlier layers. |
| Outcome: | The proposed method outperforms RoBERTa for 6 out of 8 GLUE tasks on average by 0.4%. |
Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing models treat source and target sentences as one-dimensional sequences over time, while a 2D mapping is achieved using an MDLSTM layer. |
| Approach: | They propose a multi-dimensional long short-term memory architecture for translation modelling that uses an MDLSTM layer to define the correspondence between source and target words. |
| Outcome: | The proposed model improves on two WMT 2017 tasks, showing that the source and target sentences are aligned with each other in a 2D grid. |
Transformer-Based Direct Hidden Markov Model for Machine Translation (2021.acl-srw)
Copied to clipboard
| Challenge: | Recent studies have found that word alignments produced by the multi-head cross-attention weights are poor. |
| Approach: | They propose to introduce the hidden Markov model to the transformer architecture and introduce alignment components while keeping the system monolithic. |
| Outcome: | The proposed model outperforms the baseline model but is slower in training and decoding. |
Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder (D18-1)
Copied to clipboard
| Challenge: | Unsupervised learning of cross-lingual word embeddings has fundamental limitations in translating sentences. |
| Approach: | They propose a method to improve word-by-word translation of cross-lingual embeddings using monolingual corpora without any back-translation. |
| Outcome: | The proposed system surpasses state-of-the-art unsupervised translation systems without costly iterative training. |
Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture (2020.acl-main)
Copied to clipboard
| Challenge: | Current neural networks are heavily growing in depth, with many fully connected layers. |
| Approach: | They propose to combine stabilized lottery ticket pruning with unstructured pruning to improve model performance. |
| Outcome: | The proposed pruning techniques outperform all other techniques for even higher sparsity levels. |
Does Joint Training Really Help Cascaded Speech Translation? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, in speech translation, the straightforward approach delivers state-of-the-art results, but fundamental challenges such as error propagation remain. |
| Approach: | They propose to combine a cascaded recognition system with a machine translation system to improve cascade speech translation. |
| Outcome: | The proposed methods can improve cascaded speech translation and suggest alternative training methods. |
Neural Hidden Markov Model for Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Attention-based neural machine translation models selectively focus on specific source positions to produce a translation. |
| Approach: | They propose to replace the attention component with a neural hidden Markov model that selectively focuss on specific source positions to produce a translation. |
| Outcome: | The proposed model performs better than the state-of-the-art attention-based models on the GermanEnglish and ChineseEnglish translation tasks. |
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent document-grounded dialog systems have seen an increase in popularity. |
| Approach: | They propose a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes’ theorem and propose different approximate decoding schemes. |
| Outcome: | The proposed model is more factual in terms of automatic factuality metrics than the baseline model and can be combined with a recently proposed method to control factuity in grounded dialog, CTRL. |
When and Why is Document-level Context Useful in Neural Machine Translation? (D19-65)
Copied to clipboard
| Challenge: | Recent advances in document-level NMT focus on sophisticated integration of the context, explaining its improvement with only a few selected examples or targeted test sets. |
| Approach: | They extensively quantify the causes of improvements by a document-level model in general test sets, clarifying the limit of the usefulness of document- level context in NMT. |
| Outcome: | The proposed model is not interpretable as utilizing the context, and a long context is not helpful for NMT. |