Various common deep learning architectures, such as LSTMs, GRUs, Resnets and Highway Networks, employ state passthrough connections that support training with high feed-forward depth or recurrence over many time steps. These "Passthrough Networks" architectures also enable the decoupling of the network state size from the number of parameters of the network, a possibility has been studied by \newcite{Sak2014} with their low-rank parametrization of the LSTM. In this work we extend this line of research, proposing effective, low-rank and low-rank plus diagonal matrix parametrizations for Passthrough Networks which exploit this decoupling property, reducing the data complexity and memory requirements of the network while preserving its memory capacity. This is particularly beneficial in low-resource settings as it supports expressive models with a compact parametrization less susceptible to overfitting. We present competitive experimental results on several tasks, including language modeling and a near state of the art result on sequential randomly-permuted MNIST classification, a hard task on natural data.
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a single vector per character type and a fixed set of parameters for the compositional model. Despite the compactness of this model and, more importantly, the arbitrary nature of the form-function relationship in language, our "composed" word representations yield state-of-the-art results in language modeling and part-of-speech tagging. Benefits over traditional baselines are particularly pronounced in morphologically rich languages (e.g., Turkish).
Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size of problems we are able to tackle with current hardware. Second, it remains unclear how close it matches the task loss such as the top-k error rate or other non-differentiable evaluation metrics which we aim to optimize ultimately. In this paper, we introduce an alternative classification loss function, the Z-loss, which is designed to address these two issues. Unlike the log-softmax, it has the desirable property of belonging to the spherical loss family (Vincent et al., 2015), a class of loss functions for which training can be performed very efficiently with a complexity independent of the number of output classes. We show experimentally that it significantly outperforms the other spherical loss functions previously investigated. Furthermore, we show on a word language modeling task that it also outperforms the log-softmax with respect to certain ranking scores, such as top-k scores, suggesting that the Z-loss has the flexibility to better match the task loss. These qualities thus makes the Z-loss an appealing candidate to train very efficiently large output networks such as word-language models or other extreme classification problems. On the One Billion Word (Chelba et al., 2014) dataset, we are able to train a model with the Z-loss 40 times faster than the log-softmax and more than 4 times faster than the hierarchical softmax.
Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art KenLM package. It imposes much lower memory requirements, often by orders of magnitude, and has runtimes that are either similar (for training) or comparable (for querying).
Recurrent neural networks (RNNs) are very good at modelling the flow of text, but typically need to be trained on a far larger corpus than is available for the PAN 2015 Author Identification task. This paper describes a novel approach where the output layer of a character-level RNN language model is split into several independent predictive sub-models, each representing an author, while the recurrent layer is shared by all. This allows the recurrent layer to model the language as a whole without over-fitting, while the outputs select aspects of the underlying model that reflect their author's style. The method proves competitive, ranking first in two of the four languages.
In this paper we introduce Latent Tree Language Model (LTLM), a novel approach to language modeling that encodes syntax and semantics of a given sentence as a tree of word roles. The learning phase iteratively updates the trees by moving nodes according to Gibbs sampling. We introduce two algorithms to infer a tree for a given sentence. The first one is based on Gibbs sampling. It is fast, but does not guarantee to find the most probable tree. The second one is based on dynamic programming. It is slower, but guarantees to find the most probable tree. We provide comparison of both algorithms. We combine LTLM with 4-gram Modified Kneser-Ney language model via linear interpolation. Our experiments with English and Czech corpora show significant perplexity reductions (up to 46% for English and 49% for Czech) compared with standalone 4-gram Modified Kneser-Ney language model.
Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence. We find that, in fact, an n-gram language model with a simple heuristic gives strong results on this task. Furthermore, we show that a long short-term memory (LSTM) language model is even more effective at recovering order, with our basic model outperforming a state-of-the-art syntactic model by 11.5 BLEU points. Additional data and larger beams yield further gains, at the expense of training and search time.
Language models (LMs) are statistical models that calculate probabilities over sequences of words or other discrete symbols. Currently two major paradigms for language modeling exist: count-based n-gram models, which have advantages of scalability and test-time speed, and neural LMs, which often achieve superior modeling performance. We demonstrate how both varieties of models can be unified in a single modeling framework that defines a set of probability distributions over the vocabulary of words, and then dynamically calculates mixture weights over these distributions. This formulation allows us to create novel hybrid models that combine the desirable features of count-based and neural LMs, and experiments demonstrate the advantages of these approaches.
Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding context words by hidden layers, an output layer estimates the probability of the next word. Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer. In this paper, we propose to compress neural language models by sparse word representations. In the experiments, the number of parameters in our model increases very slowly with the growth of the vocabulary size, which is almost imperceptible. Moreover, our approach not only reduces the parameter space to a large extent, but also improves the performance in terms of the perplexity measure.
We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the character-level and word-level inputs. The gate creates the final vector representation of a word by combining two distinct representations of the word. The character-level inputs are converted into vector representations of words using a bidirectional LSTM. The word-level inputs are projected into another high-dimensional space by a word lookup table. The final vector representations of words are used in the LSTM language model which predicts the next word given all the preceding words. Our model with the gating mechanism effectively utilizes the character-level inputs for rare and out-of-vocabulary words and outperforms word-level language models on several English corpora.
We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experiments show that they provide better parsing in English than any single previously published supervised generative model and better language modeling than state-of-the-art sequential RNNs in English and Chinese.
The production of color language is essential for grounded language generation. Color descriptions have many challenging properties: they can be vague, compositionally complex, and denotationally rich. We present an effective approach to generating color descriptions using recurrent neural networks and a Fourier-transformed color representation. Our model outperforms previous work on a conditional language modeling task over a large corpus of naturalistic color descriptions. In addition, probing the model's output reveals that it can accurately produce not only basic color terms but also descriptors with non-convex denotations ("greenish"), bare modifiers ("bright", "dull"), and compositional phrases ("faded teal") not seen in training.
Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores. This structured approach avoids classical biases associated with local training and unifies the training loss with the test-time usage, while preserving the proven model architecture of seq2seq and its efficient training approach. We show that our system outperforms a highly-optimized attention-based seq2seq system and other baselines on three different sequence to sequence tasks: word ordering, parsing, and machine translation.
Attention mechanisms have attracted considerable interest in image captioning due to its powerful performance. However, existing methods use only visual content as attention and whether textual context can improve attention in image captioning remains unsolved. To explore this problem, we propose a novel attention mechanism, called \textit{text-conditional attention}, which allows the caption generator to focus on certain image features given previously generated text. To obtain text-related image features for our attention model, we adopt the guiding Long Short-Term Memory (gLSTM) captioning architecture with CNN fine-tuning. Our proposed method allows joint learning of the image embedding, text embedding, text-conditional attention and language model with one network architecture in an end-to-end manner. We perform extensive experiments on the MS-COCO dataset. The experimental results show that our method outperforms state-of-the-art captioning methods on various quantitative metrics as well as in human evaluation, which supports the use of our text-conditional attention in image captioning.
To enhance developer productivity, all modern integrated development environments (IDEs) include code suggestion functionality that proposes likely next tokens at the cursor. While current IDEs work well for statically-typed languages, their reliance on type annotations means that they do not provide the same level of support for dynamic programming languages as for statically-typed languages. Moreover, suggestion engines in modern IDEs do not propose expressions or multi-statement idiomatic code. Recent work has shown that language models can improve code suggestion systems by learning from software repositories. This paper introduces a neural language model with a sparse pointer network aimed at capturing very long-range dependencies. We release a large-scale code suggestion corpus of 41M lines of Python code crawled from GitHub. On this corpus, we found standard neural language models to perform well at suggesting local phenomena, but struggle to refer to identifiers that are introduced many tokens in the past. By augmenting a neural language model with a pointer network specialized in referring to predefined classes of identifiers, we obtain a much lower perplexity and a 5 percentage points increase in accuracy for code suggestion compared to an LSTM baseline. In fact, this increase in code suggestion accuracy is due to a 13 times more accurate prediction of identifiers. Furthermore, a qualitative analysis shows this model indeed captures interesting long-range dependencies, like referring to a class member defined over 60 tokens in the past.
Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models. We propose a new Character-to-Word-to-Character (C2W2C) compositional language model that uses characters as input and output while still internally processing word level embeddings. Our preliminary experiments, using the Finnish Europarl V7 corpus, indicate that C2W2C can respond well to the challenges of morphologically rich languages such as high out of vocabulary rates, the prediction of novel words, and growing vocabulary size. Notably, the model is able to correctly score inflectional forms that are not present in the training data and sample grammatically and semantically correct Finnish sentences character by character.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in videos, spatio-temporal measurements on a network of sensors, or random walks on a vocabulary graph for natural language modeling. The proposed model combines convolutional neural networks (CNN) on graphs to identify spatial structures and RNN to find dynamic patterns. We study two possible architectures of GCRN, and apply the models to two practical problems: predicting moving MNIST data, and modeling natural language with the Penn Treebank dataset. Experiments show that exploiting simultaneously graph spatial and dynamic information about data can improve both precision and learning speed.
Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they learn, from a linguistic perspective, through various ablations to the model and the data, and by augmenting the model with an attention mechanism (GA-RNNG) to enable closer inspection. We find that explicit modeling of composition is crucial for achieving the best performance. Through the attention mechanism, we find that headedness plays a central role in phrasal representation (with the model's latent attention largely agreeing with predictions made by hand-crafted head rules, albeit with some important differences). By training grammars without nonterminal labels, we find that phrasal representations depend minimally on nonterminals, providing support for the endocentricity hypothesis.
In this work we implement a training of a Language Model (LM), using Recurrent Neural Network (RNN) and GloVe word embeddings, introduced by Pennigton et al. in [1]. The implementation is following the general idea of training RNNs for LM tasks presented in [2], but is rather using Gated Recurrent Unit (GRU) [3] for a memory cell, and not the more commonly used LSTM [4].
In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid some of the major difficulties posed by training VAE models on textual data.