In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction loss which interpolates between auto-encoding and back-translation loss components. We propose an adversarial loss to enforce generated samples to be attribute compatible and realistic. Through quantitative, qualitative and human evaluations we demonstrate that our model is capable of generating fluent sentences that better reflect the conditioning information compared to prior methods. We further demonstrate that the model is capable of simultaneously controlling multiple attributes.

Machine translation is highly sensitive to the size and quality of the training data, which has led to an increasing interest in collecting and filtering large parallel corpora. In this paper, we propose a new method for this task based on multilingual sentence embeddings. Our approach uses an encoder-decoder trained over an initial parallel corpus to build multilingual sentence representations, which are then incorporated into a new margin-based method to score, mine and filter parallel sentences. In contrast to previous approaches, which rely on nearest neighbor retrieval with a hard threshold over cosine similarity, our proposed method accounts for the scale inconsistencies of this measure, considering the margin between a given sentence pair and its closest candidates instead. Our experiments show large improvements over existing methods. We outperform the best published results on the BUCC shared task on parallel corpus mining by more than 10 F1 points. We also improve the precision from 48.9 to 83.3 on the reconstruction of 11.3M English-French sentence pairs of the UN corpus. Finally, filtering the English-German ParaCrawl corpus with our approach, we obtain 31.2 BLEU points on newstest2014, an improvement of more than one point over the best official filtered version.

In the last decade, translation services have grown exponentially to include hardware devices such as Travis Translator, earphones such as Waverly Labs' pilot, Microsoft Translator, -- which not only translates text, but also speech, images, and street signs -- Google translate, and Facebook translation. Translations are occurring faster and with greater accuracy thanks to machine translation. But what does this mean for the traditional translator? As an expatriate in Germany, I am a user of both translation services and translation software, so I was interested to find out more. I spoke with the CEO and founder of Gengo, Matt Romaine.

Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this paper, we propose a bottom-up gated hierarchical attention (GHA) mechanism for image captioning. Our proposed model employs a CNN as the decoder which is able to learn different concepts at different layers, and apparently, different concepts correspond to different areas of an image. Therefore, we develop the GHA in which low-level concepts are merged into high-level concepts and simultaneously low-level attended features pass to the top to make predictions. Our GHA significantly improves the performance of the model that only applies one level attention, for example, the CIDEr score increases from 0.923 to 0.999, which is comparable to the state-of-the-art models that employ attributes boosting and reinforcement learning (RL). We also conduct extensive experiments to analyze the CNN decoder and our proposed GHA, and we find that deeper decoders cannot obtain better performance, and when the convolutional decoder becomes deeper the model is likely to collapse during training.

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this, several probability mapping functions have been proposed and employed in literature such as softmax, sum-normalization, spherical softmax, and sparsemax, but there is very little understanding in terms how they relate with each other. Further, none of the above formulations offer an explicit control over the degree of sparsity. To address this, we develop a unified framework that encompasses all these formulations as special cases. This framework ensures simple closed-form solutions and existence of sub-gradients suitable for learning via backpropagation. Within this framework, we propose two novel sparse formulations, sparsegen-lin and sparsehourglass, that seek to provide a control over the degree of desired sparsity. We further develop novel convex loss functions that help induce the behavior of aforementioned formulations in the multilabel classification setting, showing improved performance. We also demonstrate empirically that the proposed formulations, when used to compute attention weights, achieve better or comparable performance on standard seq2seq tasks like neural machine translation and abstractive summarization.

We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-supervised nature of the Wikipedia training corpus. Finetuning on the Lang-8 corpus and ensembling yields an F0.5 of 58.3 on the CoNLL'14 benchmark and a GLEU of 62.4 on JFLEG. The combination of weakly supervised training and iterative decoding obtains an F0.5 of 48.2 on CoNLL'14 even without using any labeled GEC data.

Existing attention mechanisms, are mostly item-based in that a model is designed to attend to a single item in a collection of items (the memory). Intuitively, an area in the memory that may contain multiple items can be worth attending to as a whole. We propose area attention: a way to attend to an area of the memory, where each area contains a group of items that are either spatially adjacent when the memory has a 2-dimensional structure, such as images, or temporally adjacent for 1-dimensional memory, such as natural language sentences. Importantly, the size of an area, i.e., the number of items in an area, can vary depending on the learned coherence of the adjacent items. By giving the model the option to attend to an area of items, instead of only a single item, we hope attention mechanisms can better capture the nature of the task. Area attention can work along multi-head attention for attending to multiple areas in the memory. We evaluate area attention on two tasks: neural machine translation and image captioning, and improve upon strong (state-of-the-art) baselines in both cases. These improvements are obtainable with a basic form of area attention that is parameter free. In addition to proposing the novel concept of area attention, we contribute an efficient way for computing it by leveraging the technique of summed area tables.

Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as "learning to teach with dynamic loss functions" (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.

Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates in the softmax layer. In this paper, we introduce a novel softmax layer approximation algorithm by exploiting the clustering structure of context vectors. Our algorithm uses a light-weight screening model to predict a much smaller set of candidate words based on the given context, and then conducts an exact softmax only within that subset. Training such a procedure end-to-end is challenging as traditional clustering methods are discrete and non-differentiable, and thus unable to be used with back-propagation in the training process. Using the Gumbel softmax, we are able to train the screening model end-to-end on the training set to exploit data distribution. The algorithm achieves an order of magnitude faster inference than the original softmax layer for predicting top-$k$ words in various tasks such as beam search in machine translation or next words prediction. For example, for machine translation task on German to English dataset with around 25K vocabulary, we can achieve 20.4 times speed up with 98.9\% precision@1 and 99.3\% precision@5 with the original softmax layer prediction, while state-of-the-art ~\citep{MSRprediction} only achieves 6.7x speedup with 98.7\% precision@1 and 98.1\% precision@5 for the same task.

Abstract--Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs). We propose that by running traditionally stacked encoding branches from encoder-decoder attentionfocused architectures in parallel, that even more sequential operations can be removed from the model and thereby decrease training time. In particular, we modify the recently published attention-based architecture called Transformer by Google, by replacing sequential attention modules with parallel ones, reducing the amount of training time and substantially improving BLEU scores at the same time. Experiments over the English to German and English to French translation tasks show that our model establishes a new state of the art. Historically, statistical machine translation involved extensive work in the alignment of words and phrases developed by linguistic experts working with computer scientists [1].