Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT-14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous state of the art. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

/pdf/sequence-to-sequence-learning-with-neural-networks-4slgp125no.pdf

Sequence to Sequence Learning with Neural Networks

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge of the authors; (2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and (3) the application areas that have the potential to be impacted significantly by deep learning and that have been experiencing research growth, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.

/pdf/deep-learning-methods-and-applications-5cyi610sjz.pdf

Deep Learning: Methods and Applications

Long Short-Term Memory (LSTM) is a specific recurrent neural network (RNN) architecture that was designed to model temporal sequences and their long-range dependencies more accurately than conventional RNNs. In this paper, we explore LSTM RNN architectures for large scale acoustic modeling in speech recognition. We recently showed that LSTM RNNs are more effective than DNNs and conventional RNNs for acoustic modeling, considering moderately-sized models trained on a single machine. Here, we introduce the first distributed training of LSTM RNNs using asynchronous stochastic gradient descent optimization on a large cluster of machines. We show that a two-layer deep LSTM RNN where each LSTM layer has a linear recurrent projection layer can exceed state-of-the-art speech recognition performance. This architecture makes more effective use of model parameters than the others considered, converges quickly, and outperforms a deep feed forward neural network having an order of magnitude more parameters. Index Terms: Long Short-Term Memory, LSTM, recurrent neural network, RNN, speech recognition, acoustic modeling.

/pdf/long-short-term-memory-recurrent-neural-network-x1m1pyjq8e.pdf

Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling

Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of natural language processing (NLP). In this paper, we review significant deep learning related models and methods that have been employed for numerous NLP tasks and provide a walk-through of their evolution. We also summarize, compare and contrast the various models and put forward a detailed understanding of the past, present and future of deep learning in NLP.

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Neural networks have become increasingly popular for the task of language modeling. Whereas feed-forward networks only exploit a fixed context length to predict the next word of a sequence, conceptually, standard recurrent neural networks can take into account all of the predecessor words. On the other hand, it is well known that recurrent networks are difficult to train and therefore are unlikely to show the full potential of recurrent models. These problems are addressed by a the Long Short-Term Memory neural network architecture. In this work, we analyze this type of network on an English and a large French language modeling task. Experiments show improvements of about 8 % relative in perplexity over standard recurrent neural network LMs. In addition, we gain considerable improvements in WER on top of a state-of-the-art speech recognition system.

/pdf/lstm-neural-networks-for-language-modeling-1aw3c4nqzw.pdf

LSTM Neural Networks for Language Modeling.

Language models have traditionally been estimated based on relative frequencies, using count statistics that can be extracted from huge amounts of text data. More recently, it has been found that neural networks are particularly powerful at estimating probability distributions over word sequences, giving substantial improvements over state-of-the-art count models. However, the performance of neural network language models strongly depends on their architectural structure. This paper compares count models to feedforward, recurrent, and long short-term memory (LSTM) neural network variants on two large-vocabulary speech recognition tasks. We evaluate the models in terms of perplexity and word error rate, experimentally validating the strong correlation of the two quantities, which we find to hold regardless of the underlying type of the language model. Furthermore, neural networks incur an increased computational complexity compared to count models, and they differently model context dependences, often exceeding the number of words that are taken into account by count based approaches. These differences require efficient search methods for neural networks, and we analyze the potential improvements that can be obtained when applying advanced algorithms to the rescoring of word lattices on large-scale setups.

From feedforward to recurrent LSTM neural networks for language modeling

This work presents two different translation models using recurrent neural networks The first one is a word-based approach using word alignments Second, we present phrase-based translation models that are more consistent with phrasebased decoding Moreover, we introduce bidirectional recurrent neural models to the problem of machine translation, allowing us to use the full source sentence in our models, which is also of theoretical interest We demonstrate that our translation models are capable of improving strong baselines already including recurrent neural language models on three tasks: IWSLT 2013 German!English, BOLT Arabic!English and Chinese!English We obtain gains up to 16% BLEU and 17% TER by rescoring 1000-best lists

/pdf/translation-modeling-with-bidirectional-recurrent-neural-2whifbv7j8.pdf

Translation Modeling with Bidirectional Recurrent Neural Networks

Research on language modeling for speech recognition has increasingly focused on the application of neural networks. Two competing concepts have been developed: On the one hand, feedforward neural networks representing an n-gram approach, on the other hand recurrent neural networks that may learn context dependencies spanning more than a fixed number of predecessor words. To the best of our knowledge, no comparison has been carried out between feedforward and state-of-the-art recurrent networks when applied to speech recognition. This paper analyzes this aspect in detail on a well-tuned French speech recognition task. In addition, we propose a simple and efficient method to normalize language model probabilities across different vocabularies, and we show how to speed up training of recurrent neural networks by parallelization.

/pdf/comparison-of-feedforward-and-recurrent-neural-network-4uoe5kf1r1.pdf

Comparison of feedforward and recurrent neural network language models

RASR is the open source version of the well-proven speech recognition toolkit developed and used at RWTH Aachen University. The current version of the package includes state of the art speech recognition technology for acoustic model training and decoding. Speaker adaptation, speaker adaptive training, unsupervised training, discriminative training, lattice processing tools, flexible signal analysis, a finite state automata library, and an efficient dynamic network decoder are notable components. Comprehensive documentation, example setups for training and recognition, and tutorials are provided to support newcomers.

Martin Sundermeyer

Papers

LSTM Neural Networks for Language Modeling.

From feedforward to recurrent LSTM neural networks for language modeling

Translation Modeling with Bidirectional Recurrent Neural Networks

Comparison of feedforward and recurrent neural network language models

RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit