PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1909.06695공식 코드 · Papers with Code

Ouroboros: On Accelerating Training of Transformer-Based Language Models

Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. We also prove that our proposed algorithm is guaranteed to converge to critical points for non-convex problems. Extensive experiments on Transformer and Transformer-XL language models demonstrate that the proposed algorithm obtains a much faster speedup beyond data parallelism, with comparable or better accuracy. Code to reproduce experiments is to be found at \url{https://github.com/LaraQianYang/Ouroboros}.

arXiv:1909.06694

Beyond BLEU: Training Neural Machine Translation with Semantic Similarity

While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve final translation accuracy. However, training with BLEU has some limitations: it doesn't assign partial credit, it has a limited range of output values, and it can penalize semantically correct hypotheses if they differ lexically from the reference. In this paper, we introduce an alternative reward function for optimizing NMT systems that is based on recent work in semantic similarity. We evaluate on four disparate languages translated to English, and find that training with our proposed metric results in better translations as evaluated by BLEU, semantic similarity, and human evaluation, and also that the optimization procedure converges faster. Analysis suggests that this is because the proposed metric is more conducive to optimization, assigning partial credit and providing more diversity in scores than BLEU.

arXiv:1909.07342

Multilingual Neural Machine Translation for Zero-Resource Languages

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in translating low-resourced languages, due to the significant amount of parallel data that is required to learn useful mappings between languages. In this work, we show how the so-called multilingual NMT can help to tackle the challenges associated with low-resourced language translation. The underlying principle of multilingual NMT is to force the creation of hidden representations of words in a shared semantic space across multiple languages, thus enabling a positive parameter transfer across languages. Along this direction, we present multilingual translation experiments with three languages (English, Italian, Romanian) covering six translation directions, utilizing both recurrent neural networks and transformer (or self-attentive) neural networks. We then focus on the zero-shot translation problem, that is how to leverage multi-lingual data in order to learn translation directions that are not covered by the available training material. To this aim, we introduce our recently proposed iterative self-training method, which incrementally improves a multilingual NMT on a zero-shot direction by just relying on monolingual data. Our results on TED talks data show that multilingual NMT outperforms conventional bilingual NMT, that the transformer NMT outperforms recurrent NMT, and that zero-shot NMT outperforms conventional pivoting methods and even matches the performance of a fully-trained bilingual system.

arXiv:1909.06317

A Comparative Study on Transformer vs RNN in Speech Applications

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS benchmarks. Our experiments revealed various training tips and significant performance benefits obtained with Transformer for each task including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN. We are preparing to release Kaldi-style reproducible recipes using open source and publicly available datasets for all the ASR, ST, and TTS tasks for the community to succeed our exciting outcomes.

arXiv:1909.06091

Neural Machine Translation with 4-Bit Precision and Beyond

Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ logarithmic quantization in lieu of fixed-point quantization. However, we find bias terms are less amenable to log quantization but note they comprise a tiny fraction of the model, so we leave them uncompressed. We also propose to use an error-feedback mechanism during retraining, to preserve the compressed model as a stale gradient. We empirically show that NMT models based on Transformer or RNN architecture can be compressed up to 4-bit precision without any noticeable quality degradation. Models can be compressed up to binary precision, albeit with lower quality. The RNN architecture seems to be more robust to quantization, compared to the Transformer.

arXiv:1909.05424공식 코드 · Papers with Code

VizSeq: A Visual Analysis Toolkit for Text Generation Tasks

Automatic evaluation of text generation tasks (e.g. machine translation, text summarization, image captioning and video description) usually relies heavily on task-specific metrics, such as BLEU and ROUGE. They, however, are abstract numbers and are not perfectly aligned with human assessment. This suggests inspecting detailed examples as a complement to identify system error patterns. In this paper, we present VizSeq, a visual analysis toolkit for instance-level and corpus-level system evaluation on a wide variety of text generation tasks. It supports multimodal sources and multiple text references, providing visualization in Jupyter notebook or a web app interface. It can be used locally or deployed onto public servers for centralized data hosting and benchmarking. It covers most common n-gram based metrics accelerated with multiprocessing, and also provides latest embedding-based metrics such as BERTScore.

arXiv:1909.05362

Problems with automating translation of movie/TV show subtitles

We present 27 problems encountered in automating the translation of movie/TV show subtitles. We categorize each problem in one of the three categories viz. problems directly related to textual translation, problems related to subtitle creation guidelines, and problems due to adaptability of machine translation (MT) engines. We also present the findings of a translation quality evaluation experiment where we share the frequency of 16 key problems. We show that the systems working at the frontiers of Natural Language Processing do not perform well for subtitles and require some post-processing solutions for redressal of these problems

arXiv:1909.05356공식 코드 · Papers with Code

Entity Projection via Machine Translation for Cross-Lingual NER

Although over 100 languages are supported by strong off-the-shelf machine translation systems, only a subset of them possess large annotated corpora for named entity recognition. Motivated by this fact, we leverage machine translation to improve annotation-projection approaches to cross-lingual named entity recognition. We propose a system that improves over prior entity-projection methods by: (a) leveraging machine translation systems twice: first for translating sentences and subsequently for translating entities; (b) matching entities based on orthographic and phonetic similarity; and (c) identifying matches based on distributional statistics derived from the dataset. Our approach improves upon current state-of-the-art methods for cross-lingual named entity recognition on 5 diverse languages by an average of 4.1 points. Further, our method achieves state-of-the-art F_1 scores for Armenian, outperforming even a monolingual model trained on Armenian source data.

arXiv:1909.05246

Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems

Self-attentional models are a new paradigm for sequence modelling tasks which differ from common sequence modelling methods, such as recurrence-based and convolution-based sequence learning, in the way that their architecture is only based on the attention mechanism. Self-attentional models have been used in the creation of the state-of-the-art models in many NLP tasks such as neural machine translation, but their usage has not been explored for the task of training end-to-end task-oriented dialogue generation systems yet. In this study, we apply these models on the three different datasets for training task-oriented chatbots. Our finding shows that self-attentional models can be exploited to create end-to-end task-oriented chatbots which not only achieve higher evaluation scores compared to recurrence-based models, but also do so more efficiently.

arXiv:1909.05088

Getting Gender Right in Neural Machine Translation

Speakers of different languages must attend to and encode strikingly different aspects of the world in order to use their language correctly (Sapir, 1921; Slobin, 1996). One such difference is related to the way gender is expressed in a language. Saying "I am happy" in English, does not encode any additional knowledge of the speaker that uttered the sentence. However, many other languages do have grammatical gender systems and so such knowledge would be encoded. In order to correctly translate such a sentence into, say, French, the inherent gender information needs to be retained/recovered. The same sentence would become either "Je suis heureux", for a male speaker or "Je suis heureuse" for a female one. Apart from morphological agreement, demographic factors (gender, age, etc.) also influence our use of language in terms of word choices or even on the level of syntactic constructions (Tannen, 1991; Pennebaker et al., 2003). We integrate gender information into NMT systems. Our contribution is two-fold: (1) the compilation of large datasets with speaker information for 20 language pairs, and (2) a simple set of experiments that incorporate gender information into NMT for multiple language pairs. Our experiments show that adding a gender feature to an NMT system significantly improves the translation quality for some language pairs.

arXiv:1909.04879

Dynamic Fusion: Attentional Language Model for Neural Machine Translation

Neural Machine Translation (NMT) can be used to generate fluent output. As such, language models have been investigated for incorporation with NMT. In prior investigations, two models have been used: a translation model and a language model. The translation model's predictions are weighted by the language model with a hand-crafted ratio in advance. However, these approaches fail to adopt the language model weighting with regard to the translation history. In another line of approach, language model prediction is incorporated into the translation model by jointly considering source and target information. However, this line of approach is limited because it largely ignores the adequacy of the translation output. Accordingly, this work employs two mechanisms, the translation model and the language model, with an attentive architecture to the language model as an auxiliary element of the translation model. Compared with previous work in English--Japanese machine translation using a language model, the experimental results obtained with the proposed Dynamic Fusion mechanism improve BLEU and Rank-based Intuitive Bilingual Evaluation Scores (RIBES) scores. Additionally, in the analyses of the attention and predictivity of the language model, the Dynamic Fusion mechanism allows predictive language modeling that conforms to the appropriate grammatical structure.

arXiv:1909.03149공식 코드 · Papers with Code

Enhancing Machine Translation with Dependency-Aware Self-Attention

Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. We show the efficacy of each approach on WMT English-German and English-Turkish, and WAT English-Japanese translation tasks.

arXiv:1909.03147

Self Learning from Large Scale Code Corpus to Infer Structure of Method Invocations

Automatically generating code from a textual description of method invocation confronts challenges. There were two current research directions for this problem. One direction focuses on considering a textual description of method invocations as a separate Natural Language query and do not consider the surrounding context of the code. Another direction takes advantage of a practical large scale code corpus for providing a Machine Translation model to generate code. However, this direction got very low accuracy. In this work, we tried to improve these drawbacks by proposing MethodInfoToCode, an approach that embeds context information and optimizes the ability of learning of original Phrase-based Statistical Machine Translation (PBMT) in NLP to infer implementation of method invocation given method name and other context information. We conduct an expression prediction models learned from 2.86 million method invocations from the practical data of high qualities corpus on Github that used 6 popular libraries: JDK, Android, GWT, Joda-Time, Hibernate, and Xstream. By the evaluation, we show that if the developers only write the method name of a method invocation in a body of a method, MethodInfoToCode can predict the generated expression correctly at 73% in F1 score.

arXiv:1909.03341공식 코드 · Papers with Code

Neural Machine Translation with Byte-Level Subwords

Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese however can unnecessarily take up vocabulary slots and limit its compactness. Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue. High computational cost has however prevented it from being widely deployed or used in practice. In this paper, we investigate byte-level subwords, specifically byte-level BPE (BBPE), which is compacter than character vocabulary and has no out-of-vocabulary tokens, but is more efficient than using pure bytes only is. We claim that contextualizing BBPE embeddings is necessary, which can be implemented by a convolutional or recurrent layer. Our experiments show that BBPE has comparable performance to BPE while its size is only 1/8 of that for BPE. In the multilingual setting, BBPE maximizes vocabulary sharing across many languages and achieves better translation quality. Moreover, we show that BBPE enables transferring models between languages with non-overlapping character sets.

arXiv:1909.03493

MULE: Multimodal Universal Language Embedding

Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. We accomplish this by learning a single shared Multimodal Universal Language Embedding (MULE) which has been visually-semantically aligned across all languages. Then we learn to relate MULE to visual data as if it were a single language. Our method is not architecture specific, unlike prior work which typically learned separate branches for each language, enabling our approach to easily be adapted to many vision-language methods and tasks. Since MULE learns a single language branch in the multimodal model, we can also scale to support many languages, and languages with fewer annotations can take advantage of the good representation learned from other (more abundant) language data. We demonstrate the effectiveness of MULE on the bidirectional image-sentence retrieval task, supporting up to four languages in a single model. In addition, we show that Machine Translation can be used for data augmentation in multilingual learning, which, combined with MULE, improves mean recall by up to 21.9% on a single-language compared to prior work, with the most significant gains seen on languages with relatively few annotations. Our code is publicly available.

arXiv:1909.03750

Combining SMT and NMT Back-Translated Data for Efficient NMT

Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-translation (Sennrich et al., 2016), which consists on generating synthetic sentences by translating a set of monolingual, target-language sentences using a Machine Translation (MT) model. Generally, NMT models are used for back-translation. In this work, we analyze the performance of models when the training data is extended with synthetic data using different MT approaches. In particular we investigate back-translated data generated not only by NMT but also by Statistical Machine Translation (SMT) models and combinations of both. The results reveal that the models achieve the best performances when the training set is augmented with back-translated data created by merging different MT approaches.

arXiv:1909.02622

MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance

A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality. We validate our new metric, namely MoverScore, on a number of text generation tasks including summarization, machine translation, image captioning, and data-to-text generation, where the outputs are produced by a variety of neural and non-neural systems. Our findings suggest that metrics combining contextualized representations with a distance measure perform the best. Such metrics also demonstrate strong generalization capability across tasks. For ease-of-use we make our metrics available as web service.

arXiv:1909.02074공식 코드 · Papers with Code

Jointly Learning to Align and Translate with Transformer Models

The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional statistical word alignment models often remain the go-to solution. In this paper, we present an approach to train a Transformer model to produce both accurate translations and alignments. We extract discrete alignments from the attention probabilities learnt during regular neural machine translation model training and leverage them in a multi-task framework to optimize towards translation and alignment objectives. We demonstrate that our approach produces competitive results compared to GIZA++ trained IBM alignment models without sacrificing translation accuracy and outperforms previous attempts on Transformer model based word alignment. Finally, by incorporating IBM model alignments into our multi-task training, we report significantly better alignment accuracies compared to GIZA++ on three publicly available data sets.

arXiv:1909.02480공식 코드 · Papers with Code

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive sequence generation using latent variable models. Specifically, we turn to generative flow, an elegant technique to model complex distributions using neural networks, and design several layers of flow tailored for modeling the conditional density of sequential latent variables. We evaluate this model on three neural machine translation (NMT) benchmark datasets, achieving comparable performance with state-of-the-art non-autoregressive NMT models and almost constant decoding time w.r.t the sequence length.

arXiv:1909.02279

Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the previously generated words, which limits the parallelization capability, and makes it much slower than RNN-based ones. In this paper, we systematically analyze the time cost of different components of both the Transformer and RNN-based model. Based on it, we propose a hybrid network of self-attention and RNN structures, in which, the highly parallelizable self-attention is utilized as the encoder, and the simpler RNN structure is used as the decoder. Our hybrid network can decode 4-times faster than the Transformer. In addition, with the help of knowledge distillation, our hybrid network achieves comparable translation quality to the original Transformer.