Massive Exploration of Neural Machine Translation Architectures

Neural Machine Translation (NMT) has shown remarkable progress over the past few years with production systems now being deployed to end-users. One major drawback of current architectures is that they are expensive to train, typically requiring days to weeks of GPU time to converge. This makes exhaustive hyperparameter search, as is commonly done with other neural network architectures, prohibitively expensive. In this work, we present the first large-scale analysis of NMT architecture hyperparameters. We report empirical results and variance numbers for several hundred experimental runs, corresponding to over 250,000 GPU hours on the standard WMT English to German translation task. Our experiments lead to novel insights and practical advice for building and extending NMT architectures. As part of this contribution, we release an open-source NMT framework that enables researchers to easily experiment with novel techniques and reproduce state of the art results.

Latent Sequence Decompositions

We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall Street Journal speech recognition task. Our LSD model achieves 12.9% WER compared to a character baseline of 14.8% WER. When combined with a convolutional network on the encoder, we achieve 9.6% WER.

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically increasing model capacity without a proportional increase in computation. In practice, however, there are significant algorithmic and performance challenges. In this work, we address these challenges and finally realize the promise of conditional computation, achieving greater than 1000x improvements in model capacity with only minor losses in computational efficiency on modern GPU clusters. We introduce a Sparsely-Gated Mixture-of-Experts layer (MoE), consisting of up to thousands of feed-forward sub-networks. A trainable gating network determines a sparse combination of these experts to use for each example. We apply the MoE to the tasks of language modeling and machine translation, where model capacity is critical for absorbing the vast quantities of knowledge available in the training corpora. We present model architectures in which a MoE with up to 137 billion parameters is applied convolutionally between stacked LSTM layers. On large language modeling and machine translation benchmarks, these models achieve significantly better results than state-of-the-art at lower computational cost.

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Extending the success of deep neural networks to natural language understanding and symbolic reasoning requires complex operations and external memory. Recent neural program induction approaches have attempted to address this problem, but are typically limited to differentiable memory, and consequently cannot scale beyond small synthetic tasks. In this work, we propose the Manager-Programmer-Computer framework, which integrates neural networks with non-differentiable memory to support abstract, scalable and precise operations through a friendly neural computer interface. Specifically, we introduce a Neural Symbolic Machine, which contains a sequence-to-sequence neural "programmer", and a non-differentiable "computer" that is a Lisp interpreter with code assist. To successfully apply REINFORCE for training, we augment it with approximate gold programs found by an iterative maximum likelihood training process. NSM is able to learn a semantic parser from weak supervision over a large knowledge base. It achieves new state-of-the-art performance on WebQuestionsSP, a challenging semantic parsing dataset, with weak supervision. Compared to previous approaches, NSM is end-to-end, therefore does not rely on feature engineering or domain specific knowledge.

A Neural Conversational Model

Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules. We find that this straightforward model can generate simple conversations given a large conversational training dataset. Our preliminary results suggest that, despite optimizing the wrong objective function, the model is able to converse well. It is able extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles. On a domain-specific IT helpdesk dataset, the model can find a solution to a technical problem via conversations. On a noisy open-domain movie transcript dataset, the model can perform simple forms of common sense reasoning. As expected, we also find that the lack of consistency is a common failure mode of our model.

Using Web Co-occurrence Statistics for Improving Image Categorization

Object recognition and localization are important tasks in computer vision. The focus of this work is the incorporation of contextual information in order to improve object recognition and localization. For instance, it is natural to expect not to see an elephant to appear in the middle of an ocean. We consider a simple approach to encapsulate such common sense knowledge using co-occurrence statistics from web documents. By merely counting the number of times nouns (such as elephants, sharks, oceans, etc.) co-occur in web documents, we obtain a good estimate of expected co-occurrences in visual data. We then cast the problem of combining textual co-occurrence statistics with the predictions of image-based classifiers as an optimization problem. The resulting optimization problem serves as a surrogate for our inference procedure. Albeit the simplicity of the resulting optimization problem, it is effective in improving both recognition and localization accuracy. Concretely, we observe significant improvements in recognition and localization rates for both ImageNet Detection 2012 and Sun 2012 datasets.

Direct Optimization of Ranking Measures

Web page ranking and collaborative filtering require the optimization of sophisticated performance measures. Current Support Vector approaches are unable to optimize them directly and focus on pairwise comparisons instead. We present a new approach which allows direct optimization of the relevant loss functions. This is achieved via structured estimation in Hilbert spaces. It is most related to Max-Margin-Markov networks optimization of multivariate performance measures. Key to our approach is that during training the ranking problem can be viewed as a linear assignment problem, which can be solved by the Hungarian Marriage algorithm. At test time, a sort operation is sufficient, as our algorithm assigns a relevance score to every (document, query) pair. Experiments show that the our algorithm is fast and that it works very well.