We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Furthermore, we show that these vectors provide state-of-the-art performance on our test set for measuring syntactic and semantic word similarities.

Efficient Estimation of Word Representations in Vector Space

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences This work broadens the understanding of back-translation and investigates a number of methods to generate synthetic source sentences We find that in all but resource poor settings back-translations obtained via sampling or noised beam outputs are most effective Our analysis shows that sampling or noisy synthetic data gives a much stronger training signal than data generated by beam or greedy search We also compare how synthetic data compares to genuine bitext and study various domain effects Finally, we scale to hundreds of millions of monolingual sentences and achieve a new state of the art of 35 BLEU on the WMT’14 English-German test set

/pdf/understanding-back-translation-at-scale-2a1jm02ac2.pdf

Understanding Back-Translation at Scale.

In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition models, and here we consider three models, each one "reading" words in a different way: via 90k-way dictionary encoding, character sequence encoding, and bag-of-N-grams encoding. In the scenarios of language based and completely unconstrained text recognition we greatly improve upon state-of-the-art performance on standard datasets, using our fast, simple machinery and requiring zero data-acquisition costs.

/pdf/synthetic-data-and-artificial-neural-networks-for-natural-zydv8cdgxf.pdf

Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

We propose a new benchmark corpus to be used for measuring progress in statistical language modeling. With almost one billion words of training data, we hope this benchmark will be useful to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques. We show performance of several well-known types of language models, with the best results achieved with a recurrent neural network based language model. The baseline unpruned Kneser-Ney 5-gram model achieves perplexity 67.6; a combination of techniques leads to 35% reduction in perplexity, or 10% reduction in cross-entropy (bits), over that baseline. 
The benchmark is available as a this http URL project; besides the scripts needed to rebuild the training/held-out data, it also makes available log-probability values for each word in each of ten held-out data sets, for each of the baseline n-gram models.

One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling

Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n-1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.

/pdf/large-language-models-in-machine-translation-3wqubjuzrp.pdf

Large Language Models in Machine Translation

Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications

Encoding and adaptive, scalable accessing of distributed models

We introduce a novel precedence reordering approach based on a dependency parser to statistical machine translation systems. Similar to other preprocessing reordering approaches, our method can efficiently incorporate linguistic knowledge into SMT systems without increasing the complexity of decoding. For a set of five subject-object-verb (SOV) order languages, we show significant improvements in BLEU scores when translating from English, compared to other reordering approaches, in state-of-the-art phrase-based SMT systems.

/pdf/using-a-dependency-parser-to-improve-smt-for-subject-object-n77hbfbqsw.pdf

Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages

When trained on very large parallel corpora, the phrase table component of a machine translation system grows to consume vast computational resources. In this paper, we introduce a novel pruning criterion that places phrase table pruning on a sound theoretical foundation. Systematic experiments on four language pairs under various data conditions show that our principled approach is superior to existing ad hoc pruning methods.

/pdf/a-systematic-comparison-of-phrase-table-pruning-techniques-48d2b08pxd.pdf

Peng Xu

Papers

Large Language Models in Machine Translation

Encoding and adaptive, scalable accessing of distributed models

Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages

A Systematic Comparison of Phrase Table Pruning Techniques

Providing Alternative Translations