PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1910.08418

Controlling Utterance Length in NMT-based Word Segmentation with Attention

One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are challenged in real-world CLD settings by the small amount of available data. A possible remedy is to take advantage of glosses or translation in a foreign, well-resourced, language, which often exist for such data. In this paper, we explore and compare ways to exploit neural machine translation models to perform unsupervised boundary detection with bilingual information, notably introducing a new loss function for jointly learning alignment and segmentation. We experiment with an actual under-resourced language, Mboshi, and show that these techniques can effectively control the output segmentation length.

arXiv:1910.08216

A language processing algorithm for predicting tactical solutions to an operational planning problem under uncertainty

This paper is devoted to the prediction of solutions to a stochastic discrete optimization problem. Through an application, we illustrate how we can use a state-of-the-art neural machine translation (NMT) algorithm to predict the solutions by defining appropriate vocabularies, syntaxes and constraints. We attend to applications where the predictions need to be computed in very short computing time -- in the order of milliseconds or less. The results show that with minimal adaptations to the model architecture and hyperparameter tuning, the NMT algorithm can produce accurate solutions within the computing time budget. While these predictions are slightly less accurate than approximate stochastic programming solutions (sample average approximation), they can be computed faster and with less variability.

arXiv:1910.07012

Transfer Learning for Algorithm Recommendation

Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorithms for several datasets can be used to learn which algorithm, from a set of options, would be more suitable for a new dataset [2]. Perhaps the most popular form of meta-learning is transfer learning, which consists of transferring knowledge acquired by a machine learning algorithm in a previous learning task to increase its performance faster in another and similar task [3]. Transfer Learning has been widely applied in a variety of complex tasks such as image classification, machine translation and, speech recognition, achieving remarkable results [4,5,6,7,8]. Although transfer learning is very used in traditional or base-learning, it is still unknown if it is useful in a meta-learning setup. For that purpose, in this paper, we investigate the effects of transferring knowledge in the meta-level instead of base-level. Thus, we train a neural network on meta-datasets related to algorithm recommendation, and then using transfer learning, we reuse the knowledge learned by the neural network in other similar datasets from the same domain, to verify how transferable is the acquired meta-knowledge.

arXiv:1910.07481

Using Whole Document Context in Neural Machine Translation

In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-level translation tasks. We observe interesting cross-sentential behaviors where the model learns to use document-level information to improve translation coherence.

arXiv:1910.07475공식 코드 · Papers with Code

MLQA: Evaluating Cross-lingual Extractive Question Answering

Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English, making training QA systems in other languages challenging. An alternative to building large monolingual training datasets is to develop cross-lingual systems which can transfer to a target language without requiring training data in that language. In order to develop such systems, it is crucial to invest in high quality multilingual evaluation benchmarks to measure progress. We present MLQA, a multi-way aligned extractive QA evaluation benchmark intended to spur research in this area. MLQA contains QA instances in 7 languages, namely English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese. It consists of over 12K QA instances in English and 5K in each other language, with each QA instance being parallel between 4 languages on average. MLQA is built using a novel alignment context strategy on Wikipedia articles, and serves as a cross-lingual extension to existing extractive QA datasets. We evaluate current state-of-the-art cross-lingual representations on MLQA, and also provide machine-translation-based baselines. In all cases, transfer results are shown to be significantly behind training-language performance.

arXiv:1910.07468

Fine-grained evaluation of Quality Estimation for Machine translation based on a linguistically-motivated Test Suite

We present an alternative method of evaluating Quality Estimation systems, which is based on a linguistically-motivated Test Suite. We create a test-set consisting of 14 linguistic error categories and we gather for each of them a set of samples with both correct and erroneous translations. Then, we measure the performance of 5 Quality Estimation systems by checking their ability to distinguish between the correct and the erroneous translations. The detailed results are much more informative about the ability of each system. The fact that different Quality Estimation systems perform differently at various phenomena confirms the usefulness of the Test Suite.

arXiv:1910.07460

Fine-grained evaluation of German-English Machine Translation based on a Test Suite

We present an analysis of 16 state-of-the-art MT systems on German-English based on a linguistically-motivated test suite. The test suite has been devised manually by a team of language professionals in order to cover a broad variety of linguistic phenomena that MT often fails to translate properly. It contains 5,000 test sentences covering 106 linguistic phenomena in 14 categories, with an increased focus on verb tenses, aspects and moods. The MT outputs are evaluated in a semi-automatic way through regular expressions that focus only on the part of the sentence that is relevant to each phenomenon. Through our analysis, we are able to compare systems based on their performance on these categories. Additionally, we reveal strengths and weaknesses of particular systems and we identify grammatical phenomena where the overall performance of MT is relatively low.

arXiv:1910.07457

Linguistic evaluation of German-English Machine Translation using a Test Suite

We present the results of the application of a grammatical test suite for German$\rightarrow$English MT on the systems submitted at WMT19, with a detailed analysis for 107 phenomena organized in 14 categories. The systems still translate wrong one out of four test items in average. Low performance is indicated for idioms, modals, pseudo-clefts, multi-word expressions and verb valency. When compared to last year, there has been a improvement of function words, non-verbal agreement and punctuation. More detailed conclusions about particular systems and phenomena are also presented.

arXiv:1910.07370

Evolution of transfer learning in natural language processing

In this paper, we present a study of the recent advancements which have helped bring Transfer Learning to NLP through the use of semi-supervised training. We discuss cutting-edge methods and architectures such as BERT, GPT, ELMo, ULMFit among others. Classically, tasks in natural language processing have been performed through rule-based and statistical methodologies. However, owing to the vast nature of natural languages these methods do not generalise well and failed to learn the nuances of language. Thus machine learning algorithms such as Naive Bayes and decision trees coupled with traditional models such as Bag-of-Words and N-grams were used to usurp this problem. Eventually, with the advent of advanced recurrent neural network architectures such as the LSTM, we were able to achieve state-of-the-art performance in several natural language processing tasks such as text classification and machine translation. We talk about how Transfer Learning has brought about the well-known ImageNet moment for NLP. Several advanced architectures such as the Transformer and its variants have allowed practitioners to leverage knowledge gained from unrelated task to drastically fasten convergence and provide better performance on the target task. This survey represents an effort at providing a succinct yet complete understanding of the recent advances in natural language processing using deep learning in with a special focus on detailing transfer learning and its potential advantages.

arXiv:1910.06764

Stabilizing Transformers for Reinforcement Learning

Owing to their ability to both effectively integrate information over long time horizons and scale to massive amounts of data, self-attention architectures have recently shown breakthrough success in natural language processing (NLP), achieving state-of-the-art results in domains such as language modeling and machine translation. Harnessing the transformer's ability to process long time horizons of information could provide a similar performance boost in partially observable reinforcement learning (RL) domains, but the large-scale transformers used in NLP have yet to be successfully applied to the RL setting. In this work we demonstrate that the standard transformer architecture is difficult to optimize, which was previously observed in the supervised learning setting but becomes especially pronounced with RL objectives. We propose architectural modifications that substantially improve the stability and learning speed of the original Transformer and XL variant. The proposed architecture, the Gated Transformer-XL (GTrXL), surpasses LSTMs on challenging memory environments and achieves state-of-the-art results on the multi-task DMLab-30 benchmark suite, exceeding the performance of an external memory architecture. We show that the GTrXL, trained using the same losses, has stability and performance that consistently matches or exceeds a competitive LSTM baseline, including on more reactive tasks where memory is less critical. GTrXL offers an easy-to-train, simple-to-implement but substantially more expressive architectural alternative to the standard multi-layer LSTM ubiquitously used for RL agents in partially observable environments.

arXiv:1910.06720

Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition

Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain most of the parameters for language models and about a third for machine translation systems. In this paper, we propose Distilled Embedding, an (input/output) embedding compression method based on low-rank matrix decomposition and knowledge distillation. First, we initialize the weights of our decomposed matrices by learning to reconstruct the full pre-trained word-embedding and then fine-tune end-to-end, employing knowledge distillation on the factorized embedding. We conduct extensive experiments with various compression rates on machine translation and language modeling, using different data-sets with a shared word-embedding matrix for both embedding and vocabulary projection matrices. We show that the proposed technique is simple to replicate, with one fixed parameter controlling compression size, has higher BLEU score on translation and lower perplexity on language modeling compared to complex, difficult to tune state-of-the-art methods.

arXiv:1910.06717공식 코드 · Papers with Code

Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation

Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation. Yet these neural networks are very sensitive to architecture and hyperparameter settings. Optimizing these settings by grid or random search is computationally expensive because it requires many training runs. In this paper, we incorporate architecture search into a single training run through auto-sizing, which uses regularization to delete neurons in a network over the course of training. On very low-resource language pairs, we show that auto-sizing can improve BLEU scores by up to 3.9 points while removing one-third of the parameters from the model.

arXiv:1910.06411공식 코드 · Papers with Code

Mapping Supervised Bilingual Word Embeddings from English to low-resource languages

It is very challenging to work with low-resource languages due to the inadequate availability of data. Using a dictionary to map independently trained word embeddings into a shared vector space has proved to be very useful in learning bilingual embeddings in the past. Here we have tried to map individual embeddings of words in English and their corresponding translated words in low-resource languages like Estonian, Slovenian, Slovakian, and Hungarian. We have used a supervised learning approach. We report accuracy scores through various retrieval strategies which show that it is possible to approach challenging tasks in Natural Language Processing like machine translation for such languages, provided that we have at least some amount of proper bilingual data. We also conclude that we can follow an unsupervised learning path on monolingual text data as that is more suitable for low-resource languages.

arXiv:1910.06393

In-training Matrix Factorization for Parameter-frugal Neural Machine Translation

In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation. Using in-training matrix factorization, parameter matrices may be decomposed into the products of smaller matrices, which can compress large machine translation architectures by vastly reducing the number of learnable parameters. We apply in-training matrix factorization to different layers of standard neural architectures and show that in-training factorization is capable of reducing nearly 50% of learnable parameters without any associated loss in BLEU score. Further, we find that in-training matrix factorization is especially powerful on embedding layers, providing a simple and effective method to curtail the number of parameters with minimal impact on model performance, and, at times, an increase in performance.

arXiv:1910.06753공식 코드 · Papers with Code

On the Importance of Word Boundaries in Character-level Neural Machine Translation

Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standard approach to overcome this limitation is to segment words into subword units, typically using some external tools with arbitrary heuristics, resulting in vocabulary units not optimized for the translation task. Recent studies have shown that the same approach can be extended to perform NMT directly at the level of characters, which can deliver translation accuracy on-par with subword-based models, on the other hand, this requires relatively deeper networks. In this paper, we propose a more computationally-efficient solution for character-level NMT which implements a hierarchical decoding architecture where translations are subsequently generated at the level of words and characters. We evaluate different methods for open-vocabulary NMT in the machine translation task from English into five languages with distinct morphological typology, and show that the hierarchical decoding model can reach higher translation accuracy than the subword-level NMT model using significantly fewer parameters, while demonstrating better capacity in learning longer-distance contextual and grammatical dependencies than the standard character-level NMT model.

arXiv:1910.05535공식 코드 · Papers with Code

From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction

A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We present a fully automatic unsupervised way of extracting parallel data for training a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction.

arXiv:1910.05895공식 코드 · Papers with Code

Transformers without Tears: Improving the Normalization of Self-Attention

We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PreNorm) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, we propose $\ell_2$ normalization with a single scale parameter (ScaleNorm) for faster training and better performance. Finally, we reaffirm the effectiveness of normalizing word embeddings to a fixed length (FixNorm). On five low-resource translation pairs from TED Talks-based corpora, these changes always converge, giving an average +1.1 BLEU over state-of-the-art bilingual baselines and a new 32.8 BLEU on IWSLT'15 English-Vietnamese. We observe sharper performance curves, more consistent gradient norms, and a linear relationship between activation scaling and decoder depth. Surprisingly, in the high-resource setting (WMT'14 English-German), ScaleNorm and FixNorm remain competitive but PreNorm degrades performance.

arXiv:1910.05577공식 코드 · Papers with Code

Context-Gated Convolution

As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research on neuroscience reveals that the neurons' ability of modifying their functions dynamically according to context is essential for the perceptual tasks, which has been overlooked in most of CNNs. Motivated by this, we propose one novel Context-Gated Convolution (CGC) to explicitly modify the weights of convolutional layers adaptively under the guidance of global context. As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features. Moreover, our proposed CGC is lightweight and applicable with modern CNN architectures, and consistently improves the performance of CNNs according to extensive experiments on image classification, action recognition, and machine translation. Our code of this paper is available at https://github.com/XudongLinthu/context-gated-convolution.

arXiv:1910.06204공식 코드 · Papers with Code

Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality

Devising metrics to assess translation quality has always been at the core of machine translation (MT) research. Traditional automatic reference-based metrics, such as BLEU, have shown correlations with human judgements of adequacy and fluency and have been paramount for the advancement of MT system development. Crowd-sourcing has popularised and enabled the scalability of metrics based on human judgements, such as subjective direct assessments (DA) of adequacy, that are believed to be more reliable than reference-based automatic metrics. Finally, task-based measurements, such as post-editing time, are expected to provide a more detailed evaluation of the usefulness of translations for a specific task. Therefore, while DA averages adequacy judgements to obtain an appraisal of (perceived) quality independently of the task, and reference-based automatic metrics try to objectively estimate quality also in a task-independent way, task-based metrics are measurements obtained either during or after performing a specific task. In this paper we argue that, although expensive, task-based measurements are the most reliable when estimating MT quality in a specific task; in our case, this task is post-editing. To that end, we report experiments on a dataset with newly-collected post-editing indicators and show their usefulness when estimating post-editing effort. Our results show that task-based metrics comparing machine-translated and post-edited versions are the best at tracking post-editing effort, as expected. These metrics are followed by DA, and then by metrics comparing the machine-translated version and independent references. We suggest that MT practitioners should be aware of these differences and acknowledge their implications when deciding how to evaluate MT for post-editing purposes.

arXiv:1910.04209

On the adequacy of untuned warmup for adaptive optimization

Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and tuning warmup schedules, recent work proposes automatic variance rectification of Adam's adaptive learning rate, claiming that this rectified approach ("RAdam") surpasses the vanilla Adam algorithm and reduces the need for expensive tuning of Adam with warmup. In this work, we refute this analysis and provide an alternative explanation for the necessity of warmup based on the magnitude of the update term, which is of greater relevance to training stability. We then provide some "rule-of-thumb" warmup schedules, and we demonstrate that simple untuned warmup of Adam performs more-or-less identically to RAdam in typical practical settings. We conclude by suggesting that practitioners stick to linear warmup with Adam, with a sensible default being linear warmup over $2 / (1 - \beta_2)$ training iterations.