Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other natural language. And this demand has grown exponentially over past couple of years, considering the enormous exchange of information between different regions with different regional languages. Machine Translation poses numerous challenges, some of which are: a) Not all words in one language has equivalent word in another language b) Two given languages may have completely different structures c) Words can have more than one meaning. Owing to these challenges, along with many others, MT has been active area of research for more than five decades. Numerous methods have been proposed in the past which either aim at improving the quality of the translations generated by them, or study the robustness of these systems by measuring their performance on many different languages. In this literature review, we discuss statistical approaches (in particular word-based and phrase-based) and neural approaches which have gained widespread prominence owing to their state-of-the-art results across multiple major languages.
Lexical substitutes have found use in areas such as paraphrasing, text simplification, machine translation, word sense disambiguation, and part of speech induction. However the computational complexity of accurately identifying the most likely substitutes for a word has made large scale experiments difficult. In this paper I introduce a new search algorithm, FASTSUBS, that is guaranteed to find the K most likely lexical substitutes for a given word in a sentence based on an n-gram language model. The computation is sub-linear in both K and the vocabulary size V. An implementation of the algorithm and a dataset with the top 100 substitutes of each token in the WSJ section of the Penn Treebank are available at http://goo.gl/jzKH0.
Despite the remarkable evolution of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. Previous work largely focused on what these models learn at the representation level. We break this analysis down further and study individual dimensions (neurons) in the vector representation learned by end-to-end neural models in NLP tasks. We propose two methods: Linguistic Correlation Analysis, based on a supervised method to extract the most relevant neurons with respect to an extrinsic task, and Cross-model Correlation Analysis, an unsupervised method to extract salient neurons w.r.t. the model itself. We evaluate the effectiveness of our techniques by ablating the identified neurons and reevaluating the network's performance for two tasks: neural machine translation (NMT) and neural language modeling (NLM). We further present a comprehensive analysis of neurons with the aim to address the following questions: i) how localized or distributed are different linguistic properties in the models? ii) are certain neurons exclusive to some properties and not others? iii) is the information more or less distributed in NMT vs. NLM? and iv) how important are the neurons identified through the linguistic correlation method to the overall task? Our code is publicly available as part of the NeuroX toolkit (Dalvi et al. 2019).
In previous works, neural sequence models have been shown to improve significantly if external prior knowledge can be provided, for instance by allowing the model to access the embeddings of explicit features during both training and inference. In this work, we propose a different point of view on how to incorporate prior knowledge in a principled way, using a moment matching framework. In this approach, the standard local cross-entropy training of the sequential model is combined with a moment matching training mode that encourages the equality of the expectations of certain predefined features between the model distribution and the empirical distribution. In particular, we show how to derive unbiased estimates of some stochastic gradients that are central to the training, and compare our framework with a formally related one: policy gradient training in reinforcement learning, pointing out some important differences in terms of the kinds of prior assumptions in both approaches. Our initial results are promising, showing the effectiveness of our proposed framework.
Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to target tokens, which are then fed into the decoder as inputs. The second one transforms source-side word embeddings to target-side word embeddings through sentence-level alignment and word-level adversary learning, and then feeds the transformed word embeddings into the decoder as inputs. Experimental results show our method largely outperforms the NAT baseline~\citep{gu2017non} by $5.11$ BLEU scores on WMT14 English-German task and $4.72$ BLEU scores on WMT16 English-Romanian task.
Named entity recognition (NER) is the task to identify mentions of rigid designators from text belonging to predefined semantic types such as person, location, organization etc. NER always serves as the foundation for many natural language applications such as question answering, text summarization, and machine translation. Early NER systems got a huge success in achieving good performance with the cost of human engineering in designing domain-specific features and rules. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if the sentence is ambiguous. When translating a text, humans often create an initial understanding of the source sentence and then incrementally refine it along the translation on the target side. Starting from this intuition, we propose a novel encoder-refiner-decoder framework, which dynamically refines the source representations based on the generated target-side information at each decoding step. Since the refining operations are time-consuming, we propose a strategy, leveraging the power of reinforcement learning models, to decide when to refine at specific decoding steps. Experimental results on both Chinese-English and English-German translation tasks show that the proposed approach significantly and consistently improves translation performance over the standard encoder-decoder framework. Furthermore, when refining strategy is applied, results still show reasonable improvement over the baseline without much decrease in decoding speed.
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image classification, speech recognition and machine translation etc. While deep learning has been increasingly popular, the problem of privacy leakage becomes more and more urgent. Given the fact that the training data may contain highly sensitive information, e.g., personal medical records, directly sharing them among the users (i.e., participants) or centrally storing them in one single location may pose a considerable threat to user privacy. In this paper, we present a practical privacy-preserving collaborative deep learning system that allows users to cooperatively build a collective deep learning model with data of all participants, without direct data sharing and central data storage. In our system, each participant trains a local model with their own data and only shares model parameters with the others. To further avoid potential privacy leakage from sharing model parameters, we use functional mechanism to perturb the objective function of the neural network in the training process to achieve $\epsilon$-differential privacy. In particular, for the first time, we consider the existence of~\textit{unreliable participants}, i.e., the participants with low-quality data, and propose a solution to reduce the impact of these participants while protecting their privacy. We evaluate the performance of our system on two well-known real-world datasets for regression and classification tasks. The results demonstrate that the proposed system is robust against unreliable participants, and achieves high accuracy close to the model trained in a traditional centralized manner while ensuring rigorous privacy protection.
Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no separator between words. In order to assess the impact of the tokenization in the quality of the final translation on NMT, we experimented on five tokenizers over ten language pairs. We reached the conclusion that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs.
Deep neural networks have achieved state-of-the-art accuracies in a wide range of computer vision, speech recognition, and machine translation tasks. However the limits of memory bandwidth and computational power constrain the range of devices capable of deploying these modern networks. To address this problem, we propose SQuantizer, a new training method that jointly optimizes for both sparse and low-precision neural networks while maintaining high accuracy and providing a high compression rate. This approach brings sparsification and low-bit quantization into a single training pass, employing these techniques in an order demonstrated to be optimal. Our method achieves state-of-the-art accuracies using 4-bit and 2-bit precision for ResNet18, MobileNet-v2 and ResNet50, even with high degree of sparsity. The compression rates of 18x for ResNet18 and 17x for ResNet50, and 9x for MobileNet-v2 are obtained when SQuantizing both weights and activations within 1% and 2% loss in accuracy for ResNets and MobileNet-v2 respectively. An extension of these techniques to object detection also demonstrates high accuracy on YOLO-v3. Additionally, our method allows for fast single pass training, which is important for rapid prototyping and neural architecture search techniques. Finally extensive results from this simultaneous training approach allows us to draw some useful insights into the relative merits of sparsity and quantization.
In recent years, deep neural networks (DNNs) have been applied to various machine leaning tasks, including image recognition, speech recognition, and machine translation. However, large DNN models are needed to achieve state-of-the-art performance, exceeding the capabilities of edge devices. Model reduction is thus needed for practical use. In this paper, we point out that deep learning automatically induces group sparsity of weights, in which all weights connected to an output channel (node) are zero, when training DNNs under the following three conditions: (1) rectified-linear-unit (ReLU) activations, (2) an $L_2$-regularized objective function, and (3) the Adam optimizer. Next, we analyze this behavior both theoretically and experimentally, and propose a simple model reduction method: eliminate the zero weights after training the DNN. In experiments on MNIST and CIFAR-10 datasets, we demonstrate the sparsity with various training setups. Finally, we show that our method can efficiently reduce the model size and performs well relative to methods that use a sparsity-inducing regularizer.
Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that can process and relate information from these modalities. However, existing work learns joint representations by requiring all modalities as input and as a result, the learned representations may be sensitive to noisy or missing modalities at test time. With the recent success of sequence to sequence (Seq2Seq) models in machine translation, there is an opportunity to explore new ways of learning joint representations that may not require all input modalities at test time. In this paper, we propose a method to learn robust joint representations by translating between modalities. Our method is based on the key insight that translation from a source to a target modality provides a method of learning joint representations using only the source modality as input. We augment modality translations with a cycle consistency loss to ensure that our joint representations retain maximal information from all modalities. Once our translation model is trained with paired multimodal data, we only need data from the source modality at test time for final sentiment prediction. This ensures that our model remains robust from perturbations or missing information in the other modalities. We train our model with a coupled translation-prediction objective and it achieves new state-of-the-art results on multimodal sentiment analysis datasets: CMU-MOSI, ICT-MMMO, and YouTube. Additional experiments show that our model learns increasingly discriminative joint representations with more input modalities while maintaining robustness to missing or perturbed modalities.
Past years have witnessed rapid developments in Neural Machine Translation (NMT). Most recently, with advanced modeling and training techniques, the RNN-based NMT (RNMT) has shown its potential strength, even compared with the well-known Transformer (self-attentional) model. Although the RNMT model can possess very deep architectures through stacking layers, the transition depth between consecutive hidden states along the sequential axis is still shallow. In this paper, we further enhance the RNN-based NMT through increasing the transition depth between consecutive hidden states and build a novel Deep Transition RNN-based Architecture for Neural Machine Translation, named DTMT. This model enhances the hidden-to-hidden transition with multiple non-linear transformations, as well as maintains a linear transformation path throughout this deep transition by the well-designed linear transformation mechanism to alleviate the gradient vanishing problem. Experiments show that with the specially designed deep transition modules, our DTMT can achieve remarkable improvements on translation quality. Experimental results on Chinese->English translation task show that DTMT can outperform the Transformer model by +2.09 BLEU points and achieve the best results ever reported in the same dataset. On WMT14 English->German and English->French translation tasks, DTMT shows superior quality to the state-of-the-art NMT systems, including the Transformer and the RNMT+.
E-commerce platforms categorize their products into a multi-level taxonomy tree with thousands of leaf categories. Conventional methods for product categorization are typically based on machine learning classification algorithms. These algorithms take product information as input (e.g., titles and descriptions) to classify a product into a leaf category. In this paper, we propose a new paradigm based on machine translation. In our approach, we translate a product's natural language description into a sequence of tokens representing a root-to-leaf path in a product taxonomy. In our experiments on two large real-world datasets, we show that our approach achieves better predictive accuracy than a state-of-the-art classification system for product categorization. In addition, we demonstrate that our machine translation models can propose meaningful new paths between previously unconnected nodes in a taxonomy tree, thereby transforming the taxonomy into a directed acyclic graph (DAG). We discuss how the resultant taxonomy DAG promotes user-friendly navigation, and how it is more adaptable to new products.
Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification. Despite its tremendous popularity, the security vulnerabilities of DLTU are still largely unknown, which is highly concerning given its increasing use in security-sensitive applications such as sentiment analysis and toxic content detection. In this paper, we show that DLTU is inherently vulnerable to adversarial text attacks, in which maliciously crafted texts trigger target DLTU systems and services to misbehave. Specifically, we present TextBugger, a general attack framework for generating adversarial texts. In contrast to prior works, TextBugger differs in significant ways: (i) effective -- it outperforms state-of-the-art attacks in terms of attack success rate; (ii) evasive -- it preserves the utility of benign text, with 94.9\% of the adversarial text correctly recognized by human readers; and (iii) efficient -- it generates adversarial text with computational complexity sub-linear to the text length. We empirically evaluate TextBugger on a set of real-world DLTU systems and services used for sentiment analysis and toxic content detection, demonstrating its effectiveness, evasiveness, and efficiency. For instance, TextBugger achieves 100\% success rate on the IMDB dataset based on Amazon AWS Comprehend within 4.61 seconds and preserves 97\% semantic similarity. We further discuss possible defense mechanisms to mitigate such attack and the adversary's potential countermeasures, which leads to promising directions for further research.
Maximum-likelihood estimation (MLE) is widely used in sequence to sequence tasks for model training. It uniformly treats the generation/prediction of each target token as multi-class classification, and yields non-smooth prediction probabilities: in a target sequence, some tokens are predicted with small probabilities while other tokens are with large probabilities. According to our empirical study, we find that the non-smoothness of the probabilities results in low quality of generated sequences. In this paper, we propose a sentence-wise regularization method which aims to output smooth prediction probabilities for all the tokens in the target sequence. Our proposed method can automatically adjust the weights and gradients of each token in one sentence to ensure the predictions in a sequence uniformly well. Experiments on three neural machine translation tasks and one text summarization task show that our method outperforms conventional MLE loss on all these tasks and achieves promising BLEU scores on WMT14 English-German and WMT17 Chinese-English translation task.
The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent types; and it has a large memory footprint. We propose a general technique for replacing the softmax layer with a continuous embedding layer. Our primary innovations are a novel probabilistic loss, and a training and inference procedure in which we generate a probability distribution over pre-trained word embeddings, instead of a multinomial distribution over the vocabulary obtained via softmax. We evaluate this new class of sequence-to-sequence models with continuous outputs on the task of neural machine translation. We show that our models obtain upto 2.5x speed-up in training time while performing on par with the state-of-the-art models in terms of translation quality. These models are capable of handling very large vocabularies without compromising on translation quality. They also produce more meaningful errors than in the softmax-based models, as these errors typically lie in a subspace of the vector space of the reference translations.
In the present article, we identified the qualitative differences between Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) outputs. We have tried to answer two important questions: 1. Does NMT perform equivalently well with respect to SMT and 2. Does it add extra flavor in improving the quality of MT output by employing simple sentences as training units. In order to obtain insights, we have developed three core models viz., SMT model based on Moses toolkit, followed by character and word level NMT models. All of the systems use English-Hindi and English-Bengali language pairs containing simple sentences as well as sentences of other complexity. In order to preserve the translations semantics with respect to the target words of a sentence, we have employed soft-attention into our word level NMT model. We have further evaluated all the systems with respect to the scenarios where they succeed and fail. Finally, the quality of translation has been validated using BLEU and TER metrics along with manual parameters like fluency, adequacy etc. We observed that NMT outperforms SMT in case of simple sentences whereas SMT outperforms in case of all types of sentence.
Machine translation (MT) is an area of study in Natural Language processing which deals with the automatic translation of human language, from one language to another by the computer. Having a rich research history spanning nearly three decades, Machine translation is one of the most sought after area of research in the linguistics and computational community. In this paper, we investigate the models based on deep learning that have achieved substantial progress in recent years and becoming the prominent method in MT. We shall discuss the two main deep-learning based Machine Translation methods, one at component or domain level which leverages deep learning models to enhance the efficacy of Statistical Machine Translation (SMT) and end-to-end deep learning models in MT which uses neural networks to find correspondence between the source and target languages using the encoder-decoder architecture. We conclude this paper by providing a time line of the major research problems solved by the researchers and also provide a comprehensive overview of present areas of research in Neural Machine Translation.
We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent variable to model features of the translation process. We extend this model with a co-attention mechanism motivated by Parikh et al. in the inference network. Compared to the vision domain, latent variable models for text face additional challenges due to the discrete nature of language, namely posterior collapse. We experiment with different approaches to mitigate this issue. We show that our conditional variational model improves upon both discriminative attention-based translation and the variational baseline presented in Zhang et al. Finally, we present some exploration of the learned latent space to illustrate what the latent variable is capable of capturing. This is the first reported conditional variational model for text that meaningfully utilizes the latent variable without weakening the translation model.