Phil Blunsom

is this you? claim profile


Research Scientist at Oxford University and DeepMind

  • Learning and Evaluating General Linguistic Intelligence

    We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, we analyze state-of-the-art natural language understanding models and conduct an extensive empirical investigation to evaluate them against these criteria through a series of experiments that assess the task-independence of the knowledge being acquired by the learning process. In addition to task performance, we propose a new evaluation metric based on an online encoding of the test data that quantifies how quickly an existing agent (model) learns a new task. Our results show that while the field has made impressive progress in terms of model architectures that generalize to many tasks, these models still require a lot of in-domain training examples (e.g., for fine tuning, training task-specific modules), and are prone to catastrophic forgetting. Moreover, we find that far from solving general tasks (e.g., document question answering), our models are overfitting to the quirks of particular datasets (e.g., SQuAD). We discuss missing components and conjecture on how to make progress toward general linguistic intelligence.

    01/31/2019 ∙ by Dani Yogatama, et al. ∙ 8 share

    read it

  • Neural Arithmetic Logic Units

    Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates. We call this module a neural arithmetic logic unit (NALU), by analogy to the arithmetic logic unit in traditional processors. Experiments show that NALU-enhanced neural networks can learn to track time, perform arithmetic over images of numbers, translate numerical language into real-valued scalars, execute computer code, and count objects in images. In contrast to conventional architectures, we obtain substantially better generalization both inside and outside of the range of numerical values encountered during training, often extrapolating orders of magnitude beyond trained numerical ranges.

    08/01/2018 ∙ by Andrew Trask, et al. ∙ 6 share

    read it

  • Encoding Spatial Relations from Natural Language

    Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world. In particular, spatial relations are encoded in a way that is inconsistent with human spatial reasoning and lacking invariance to viewpoint changes. We present a system capable of capturing the semantics of spatial relations such as behind, left of, etc from natural language. Our key contributions are a novel multi-modal objective based on generating images of scenes from their textual descriptions, and a new dataset on which to train it. We demonstrate that internal representations are robust to meaning preserving transformations of descriptions (paraphrase invariance), while viewpoint invariance is an emergent property of the system.

    07/04/2018 ∙ by Tiago Ramalho, et al. ∙ 2 share

    read it

  • Optimizing Performance of Recurrent Neural Networks on GPUs

    As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these networks. While GPUs have become the hardware of choice for training and deploying recurrent models, the implementations employed often make use of only basic optimizations for these architectures. In this article we demonstrate that by exposing parallelism between operations within the network, an order of magnitude speedup across a range of network sizes can be achieved over a naive implementation. We describe three stages of optimization that have been incorporated into the fifth release of NVIDIA's cuDNN: firstly optimizing a single cell, secondly a single layer, and thirdly the entire network.

    04/07/2016 ∙ by Jeremy Appleyard, et al. ∙ 0 share

    read it

  • Learning to Transduce with Unbounded Memory

    Recently, strong results have been demonstrated by Deep Recurrent Neural Networks on natural language transduction problems. In this paper we explore the representational power of these models using synthetic grammars designed to exhibit phenomena similar to those found in real transduction problems such as machine translation. These experiments lead us to propose new memory-based recurrent networks that implement continuously differentiable analogues of traditional data structures such as Stacks, Queues, and DeQues. We show that these architectures exhibit superior generalisation performance to Deep RNNs and are often able to learn the underlying generating algorithms in our transduction experiments.

    06/08/2015 ∙ by Edward Grefenstette, et al. ∙ 0 share

    read it

  • Semantic Parsing with Semi-Supervised Sequential Autoencoders

    We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms.

    09/29/2016 ∙ by Tomáš Kočiský, et al. ∙ 0 share

    read it

  • Online Segment to Segment Neural Transduction

    We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders that have to read and memorize the entire input sequence in their fixed-length hidden states before producing any output. It is different from previous attentive models in that, instead of treating the attention weights as output of a deterministic function, our model assigns attention weights to a sequential latent variable which can be marginalized out and permits online generation. Experiments on abstractive sentence summarization and morphological inflection show significant performance gains over the baseline encoder-decoders.

    09/26/2016 ∙ by Lei Yu, et al. ∙ 0 share

    read it

  • Language as a Latent Variable: Discrete Generative Models for Sentence Compression

    In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and apply it to the task of compressing sentences. In this application the generative model first draws a latent summary sentence from a background language model, and then subsequently draws the observed sentence conditioned on this latent summary. In our empirical evaluation we show that generative formulations of both abstractive and extractive compression yield state-of-the-art results when trained on a large amount of supervised data. Further, we explore semi-supervised compression scenarios where we show that it is possible to achieve performance competitive with previously proposed supervised models while training on a fraction of the supervised data.

    09/23/2016 ∙ by Yishu Miao, et al. ∙ 0 share

    read it

  • Teaching Machines to Read and Comprehend

    Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

    06/10/2015 ∙ by Karl Moritz Hermann, et al. ∙ 0 share

    read it

  • Stochastic Collapsed Variational Inference for Sequential Data

    Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm in the sequential data setting. Our algorithm is applicable to both finite hidden Markov models and hierarchical Dirichlet process hidden Markov models, and to any datasets generated by emission distributions in the exponential family. Our experiment results on two discrete datasets show that our inference is both more efficient and more accurate than its uncollapsed version, stochastic variational inference.

    12/05/2015 ∙ by Pengyu Wang, et al. ∙ 0 share

    read it

  • Stochastic Collapsed Variational Inference for Hidden Markov Models

    Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm for hidden Markov models, in a sequential data setting. Given a collapsed hidden Markov Model, we break its long Markov chain into a set of short subchains. We propose a novel sum-product algorithm to update the posteriors of the subchains, taking into account their boundary transitions due to the sequential dependencies. Our experiments on two discrete datasets show that our collapsed algorithm is scalable to very large datasets, memory efficient and significantly more accurate than the existing uncollapsed algorithm.

    12/05/2015 ∙ by Pengyu Wang, et al. ∙ 0 share

    read it