In this paper, we propose a novel neural network model called RNN Encoder‐ Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixedlength vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder‐Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.

/pdf/learning-phrase-representations-using-rnn-encoder-decoder-74734oka8k.pdf

Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation

In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models. It builds upon a few projects, most notably Lua Torch, Chainer, and HIPS Autograd [4], and provides a high performance environment with easy access to automatic differentiation of models executed on different devices (CPU and GPU). To make prototyping easier, PyTorch does not follow the symbolic approach used in many other deep learning frameworks, but focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead. Note that this preprint is a draft of certain sections from an upcoming paper covering all PyTorch features.

/pdf/automatic-differentiation-in-pytorch-gbuafkf7qo.pdf

Automatic differentiation in PyTorch

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. 
In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. 
We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it was designed from first principles to support an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several commonly used benchmarks.

/pdf/pytorch-an-imperative-style-high-performance-deep-learning-59vlz5u10y.pdf

We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

/pdf/moses-open-source-toolkit-for-statistical-machine-3pmfuwk8uc.pdf

Moses: Open Source Toolkit for Statistical Machine Translation

We present a statistical phrase-based translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information. Thus it can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment. In our experiments using BLEU as a metric, the hierarchical phrase-based model achieves a relative improvement of 7.5% over Pharaoh, a state-of-the-art phrase-based system.

/pdf/a-hierarchical-phrase-based-model-for-statistical-machine-1xejmbxuk5.pdf

A Hierarchical Phrase-Based Model for Statistical Machine Translation

We present a statistical machine translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a parallel text without any syntactic annotations. Thus it can be seen as combining fundamental ideas from both syntax-based translation and phrase-based translation. We describe our system's training and decoding methods in detail, and evaluate it for translation speed and translation accuracy. Using BLEU as a metric of translation accuracy, we find that our system performs significantly better than the Alignment Template System, a state-of-the-art phrase-based system.

Hierarchical Phrase-Based Translation

We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives. In DyNet's dynamic declaration strategy, computation graph construction is mostly transparent, being implicitly constructed by executing procedural code that computes the network outputs, and the user is free to use different network structures for each input. Dynamic declaration thus facilitates the implementation of more complicated network architectures, and DyNet is specifically designed to allow users to implement their models in a way that is idiomatic in their preferred programming language (C++ or Python). One challenge with dynamic declaration is that because the symbolic computation graph is defined anew for every training example, its construction must have low overhead. To achieve this, DyNet has an optimized C++ backend and lightweight graph representation. Experiments show that DyNet's speeds are faster than or comparable with static declaration toolkits, and significantly faster than Chainer, another dynamic declaration toolkit. DyNet is released open-source under the Apache 2.0 license and available at this http URL.

DyNet: The Dynamic Neural Network Toolkit

We discuss the relevance of k-best parsing to recent applications in natural language processing, and develop efficient algorithms for k-best trees in the framework of hypergraph parsing. To demonstrate the efficiency, scalability and accuracy of these algorithms, we present experiments on Bikel's implementation of Collins' lexicalized PCFG model, and on Chiang's CFG-based decoder for hierarchical phrase-based translation. We show in particular how the improved output of our algorithms has the potential to improve results from parse reranking systems and other applications.

Better k-best Parsing

Efficient decoding has been a fundamental problem in machine translation, especially with an integrated language model which is essential for achieving good translation quality. We develop faster approaches for this problem based on k-best parsing algorithms and demonstrate their effectiveness on both phrase-based and syntax-based MT systems. In both cases, our methods achieve significant speed improvements, often by more than a factor of ten, over the conventional beam-search method at the same levels of search error and translation accuracy.

/pdf/forest-rescoring-faster-decoding-with-integrated-language-4lyrxaf0ha.pdf

David Chiang

Papers

A Hierarchical Phrase-Based Model for Statistical Machine Translation

Hierarchical Phrase-Based Translation

DyNet: The Dynamic Neural Network Toolkit

Better k-best Parsing

Forest Rescoring: Faster Decoding with Integrated Language Models