Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to incorporate the spatio-structural patterns of Chinese glyphs as rendered in raw pixels. In the context of two basic Chinese NLP tasks of language modeling and word segmentation, the model learns to represent each character's task-relevant semantic and syntactic information in the character-level embedding.
Words in some natural languages can have a composite structure. Elements of this structure include the root (that could also be composite), prefixes and suffixes with which various nuances and relations to other words can be expressed. Thus, in order to build a proper word representation one must take into account its internal structure. From a corpus of texts we extract a set of frequent subwords and from the latter set we select patterns, i.e. subwords which encapsulate information on character $n$-gram regularities. The selection is made using the pattern-based Conditional Random Field model with $l_1$ regularization. Further, for every word we construct a new sequence over an alphabet of patterns. The new alphabet's symbols confine a local statistical context stronger than the characters, therefore they allow better representations in ${\mathbb{R}}^n$ and are better building blocks for word representation. In the task of subword-aware language modeling, pattern-based models outperform character-based analogues by 2-20 perplexity points. Also, a recurrent neural network in which a word is represented as a sum of embeddings of its patterns is on par with a competitive and significantly more sophisticated character-based convolutional architecture.
We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.
Mobile devices use language models to suggest words and phrases for use in text entry. Traditional language models are based on contextual word frequency in a static corpus of text. However, certain types of phrases, when offered to writers as suggestions, may be systematically chosen more often than their frequency would predict. In this paper, we propose the task of generating suggestions that writers accept, a related but distinct task to making accurate predictions. Although this task is fundamentally interactive, we propose a counterfactual setting that permits offline training and evaluation. We find that even a simple language model can capture text characteristics that improve acceptability.
This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models. We proposed a method for on-the-fly construction and exploitation of word embeddings in both the input and output layers of a neural model by tracking contexts. This extends the dynamic entity representation used in Kobayashi et al. (2016) and incorporates a copy mechanism proposed independently by Gu et al. (2016) and Gulcehre et al. (2016). In addition, we construct a new task and dataset called Anonymized Language Modeling for evaluating the ability to capture word meanings while reading. Experiments conducted using our novel dataset show that the proposed variant of RNN language model outperformed the baseline model. Furthermore, the experiments also demonstrate that dynamic updates of an output layer help a model predict reappearing entities, whereas those of an input layer are effective to predict words following reappearing entities.
The concepts of unitary evolution matrices and associative memory have boosted the field of Recurrent Neural Networks (RNN) to state-of-the-art performance in a variety of sequential tasks. However, RNN still have a limited capacity to manipulate long-term memory. To bypass this weakness the most successful applications of RNN use external techniques such as attention mechanisms. In this paper we propose a novel RNN model that unifies the state-of-the-art approaches: Rotational Unit of Memory (RUM). The core of RUM is its rotational operation, which is, naturally, a unitary matrix, providing architectures with the power to learn long-term dependencies by overcoming the vanishing and exploding gradients problem. Moreover, the rotational unit also serves as associative memory. We evaluate our model on synthetic memorization, question answering and language modeling tasks. RUM learns the Copying Memory task completely and improves the state-of-the-art result in the Recall task. RUM's performance in the bAbI Question Answering task is comparable to that of models with attention mechanism. We also improve the state-of-the-art result to 1.189 bits-per-character (BPC) loss in the Character Level Penn Treebank (PTB) task, which is to signify the applications of RUM to real-world sequential data. The universality of our construction, at the core of RNN, establishes RUM as a promising approach to language modeling, speech recognition and machine translation.
In this paper, we introduce a novel type of Rectified Linear Unit (ReLU), called a Dual Rectified Linear Unit (DReLU). A DReLU, which comes with an unbounded positive and negative image, can be used as a drop-in replacement for a tanh activation function in the recurrent step of Quasi-Recurrent Neural Networks (QRNNs) (Bradbury et al. (2017)). Similar to ReLUs, DReLUs are less prone to the vanishing gradient problem, they are noise robust, and they induce sparse activations. We independently reproduce the QRNN experiments of Bradbury et al. (2017) and compare our DReLU-based QRNNs with the original tanh-based QRNNs and Long Short-Term Memory networks (LSTMs) on sentiment classification and word-level language modeling. Additionally, we evaluate on character-level language modeling, showing that we are able to stack up to eight QRNN layers with DReLUs, thus making it possible to improve the current state-of-the-art in character-level language modeling over shallow architectures based on LSTMs.
Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We unify successful ideas from recently proposed architectures into a stochastic recurrent model: each step in the sequence is associated with a latent variable that is used to condition the recurrent dynamics for future steps. Training is performed with amortized variational inference where the approximate posterior is augmented with a RNN that runs backward through the sequence. In addition to maximizing the variational lower bound, we ease training of the latent variables by adding an auxiliary cost which forces them to reconstruct the state of the backward recurrent network. This provides the latent variables with a task-independent objective that enhances the performance of the overall model. We found this strategy to perform better than alternative approaches such as KL annealing. Although being conceptually simple, our model achieves state-of-the-art results on standard speech benchmarks such as TIMIT and Blizzard and competitive performance on sequential MNIST. Finally, we apply our model to language modeling on the IMDB dataset where the auxiliary cost helps in learning interpretable latent variables. Source Code: \url{https://github.com/anirudh9119/zforcing_nips17}
Recently, FPGA has been increasingly applied to problems such as speech recognition, machine learning, and cloud computation such as the Bing search engine used by Microsoft. This is due to FPGAs great parallel computation capacity as well as low power consumption compared to general purpose processors. However, these applications mainly focus on large scale FPGA clusters which have an extreme processing power for executing massive matrix or convolution operations but are unsuitable for portable or mobile applications. This paper describes research on single-FPGA platform to explore the applications of FPGAs in these fields. In this project, we design a Deep Recurrent Neural Network (DRNN) Language Model (LM) and implement a hardware accelerator with AXI Stream interface on a PYNQ board which is equipped with a XILINX ZYNQ SOC XC7Z020 1CLG400C. The PYNQ has not only abundant programmable logic resources but also a flexible embedded operation system, which makes it suitable to be applied in the natural language processing field. We design the DRNN language model with Python and Theano, train the model on a CPU platform, and deploy the model on a PYNQ board to validate the model with Jupyter notebook. Meanwhile, we design the hardware accelerator with Overlay, which is a kind of hardware library on PYNQ, and verify the acceleration effect on the PYNQ board. Finally, we have found that the DRNN language model can be deployed on the embedded system smoothly and the Overlay accelerator with AXI Stream interface performs at 20 GOPS processing throughput, which constitutes a 70.5X and 2.75X speed up compared to the work in Ref.30 and Ref.31 respectively.
Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable models without handcrafted features. However, in many cases, it is hard to obtain sufficient annotations to train these models. In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task. Besides word-level knowledge contained in pre-trained word embeddings, character-aware neural language models are incorporated to extract character-level knowledge. Transfer learning techniques are further adopted to mediate different components and guide the language model towards the key knowledge. Comparing to previous methods, these task-specific knowledge allows us to adopt a more concise model and conduct more efficient training. Different from most transfer learning methods, the proposed framework does not rely on any additional supervision. It extracts knowledge from self-contained order information of training sequences. Extensive experiments on benchmark datasets demonstrate the effectiveness of leveraging character-level knowledge and the efficiency of co-training. For example, on the CoNLL03 NER task, model training completes in about 6 hours on a single GPU, reaching F1 score of 91.71$\pm$0.10 without using any extra annotation.
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neural approaches on this task as well as strong statistical machine translation-based systems with neural and task-specific features trained on the same data. Our analysis shows the superiority of convolutional neural networks over recurrent neural networks such as long short-term memory (LSTM) networks in capturing the local context via attention, and thereby improving the coverage in correcting grammatical errors. By ensembling multiple models, and incorporating an N-gram language model and edit features via rescoring, our novel method becomes the first neural approach to outperform the current state-of-the-art statistical machine translation-based approach, both in terms of grammaticality and fluency.
Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters through words to sentences, it is not apparent in current language models. We propose to improve the representation in sequence models by augmenting current approaches with an autoencoder that is forced to compress the sequence through an intermediate discrete latent space. In order to propagate gradients though this discrete representation we introduce an improved semantic hashing technique. We show that this technique performs well on a newly proposed quantitative efficiency measure. We also analyze latent codes produced by the model showing how they correspond to words and phrases. Finally, we present an application of the autoencoder-augmented model to generating diverse translations.
Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for "novel" and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines. The code is available at https://github.com/lancopku/DPGAN
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD is redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270x to 600x without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile. Code is available at: https://github.com/synxlin/deep-gradient-compression.
We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate collaborative filtering research.We introduce a generative model with multinomial likelihood and use Bayesian inference for parameter estimation. Despite widespread use in language modeling and economics, the multinomial likelihood receives less attention in the recommender systems literature. We introduce a different regularization parameter for the learning objective, which proves to be crucial for achieving competitive performance. Remarkably, there is an efficient way to tune the parameter using annealing. The resulting model and learning algorithm has information-theoretic connections to maximum entropy discrimination and the information bottleneck principle. Empirically, we show that the proposed approach significantly outperforms several state-of-the-art baselines, including two recently-proposed neural network approaches, on several real-world datasets. We also provide extended experiments comparing the multinomial likelihood with other commonly used likelihood functions in the latent factor collaborative filtering literature and show favorable results. Finally, we identify the pros and cons of employing a principled Bayesian inference approach and characterize settings where it provides the most significant improvements.
We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models (including the majority of neural language models) is limited by a Softmax bottleneck. Given that natural language is highly context-dependent, this further implies that in practice Softmax with distributed word embeddings does not have enough capacity to model natural language. We propose a simple and effective method to address this issue, and improve the state-of-the-art perplexities on Penn Treebank and WikiText-2 to 47.69 and 40.68 respectively. The proposed method also excels on the large-scale 1B Word dataset, outperforming the baseline by over 5.6 points in perplexity.
Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et al., 2016) and neural machine translation (Shi et al., 2016). In contrast, the ability to model structured data with non-recurrent neural networks has received little attention despite their success in many NLP tasks (Gehring et al., 2017; Vaswani et al., 2017). In this work, we compare the two architectures---recurrent versus non-recurrent---with respect to their ability to model hierarchical structure and find that recurrency is indeed important for this purpose.
In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of possible paths through a sentence and marginalize across this lattice to calculate sequence probabilities or optimize parameters. This approach allows us to seamlessly incorporate linguistic intuitions - including polysemy and existence of multi-word lexical items - into our language model. Experiments on multiple language modeling tasks show that English neural lattice language models that utilize polysemous embeddings are able to improve perplexity by 9.95% relative to a word-level baseline, and that a Chinese model that handles multi-character tokens is able to improve perplexity by 20.94% relative to a character-level baseline.
When a recurrent neural network language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN -- conditioning the language model by `injecting' image features -- or in a layer following the RNN -- conditioning the language model by `merging' image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN's hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.
We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization layers. We explore the training of deep vanilla recurrent neural networks (RNNs) with up to 144 layers, and show that bipolar activation functions help learning in this setting. On the Penn Treebank and Text8 language modeling tasks we obtain competitive results, improving on the best reported results for non-gated networks. In experiments with convolutional neural networks without batch normalization, we find that bipolar activations produce a faster drop in training error, and results in a lower test error on the CIFAR-10 classification task.