PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1805.00631공식 코드 · Papers with Code

Accelerating Neural Transformer via an Average Attention Network

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer. The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network. We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model. With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance. We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.

arXiv:1805.03330공식 코드 · Papers with Code

Character-level Chinese-English Translation through ASCII Encoding

Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They mainly do well for Indo-European language pairs, where the languages share the same writing system. However, for translating between Chinese and English, the gap between the two different writing systems poses a major challenge because of a lack of systematic correspondence between the individual linguistic units. In this paper, we enable character-level NMT for Chinese, by breaking down Chinese characters into linguistic units similar to that of Indo-European languages. We use the Wubi encoding scheme, which preserves the original shape and semantic information of the characters, while also being reversible. We show promising results from training Wubi-based models on the character- and subword-level with recurrent as well as convolutional models.

arXiv:1805.02937

Improving Character-level Japanese-Chinese Neural Machine Translation with Radicals as an Additional Input Feature

In recent years, Neural Machine Translation (NMT) has been proven to get impressive results. While some additional linguistic features of input words improve word-level NMT, any additional character features have not been used to improve character-level NMT so far. In this paper, we show that the radicals of Chinese characters (or kanji), as a character feature information, can be easily provide further improvements in the character-level NMT. In experiments on WAT2016 Japanese-Chinese scientific paper excerpt corpus (ASPEC-JP), we find that the proposed method improves the translation quality according to two aspects: perplexity and BLEU. The character-level NMT with the radical input feature's model got a state-of-the-art result of 40.61 BLEU points in the test set, which is an improvement of about 8.6 BLEU points over the best system on the WAT2016 Japanese-to-Chinese translation subtask with ASPEC-JP. The improvements over the character-level NMT with no additional input feature are up to about 1.5 and 1.4 BLEU points in the development-test set and the test set of the corpus, respectively.

arXiv:1805.02400

Stay On-Topic: Generating Context-specific Fake Restaurant Reviews

Automatically generated fake restaurant reviews are a threat to online review systems. Recent research has shown that users have difficulties in detecting machine-generated fake reviews hiding among real restaurant reviews. The method used in this work (char-LSTM ) has one drawback: it has difficulties staying in context, i.e. when it generates a review for specific target entity, the resulting review may contain phrases that are unrelated to the target, thus increasing its detectability. In this work, we present and evaluate a more sophisticated technique based on neural machine translation (NMT) with which we can generate reviews that stay on-topic. We test multiple variants of our technique using native English speakers on Amazon Mechanical Turk. We demonstrate that reviews generated by the best variant have almost optimal undetectability (class-averaged F-score 47%). We conduct a user study with skeptical users and show that our method evades detection more frequently compared to the state-of-the-art (average evasion 3.2/4 vs 1.5/4) with statistical significance, at level {\alpha} = 1% (Section 4.3). We develop very effective detection tools and reach average F-score of 97% in classifying these. Although fake reviews are very effective in fooling people, effective automatic detection is still feasible.

arXiv:1805.01565

Incorporating Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level

In neural machine translation (NMT), researchers face the challenge of un-seen (or out-of-vocabulary OOV) words translation. To solve this, some researchers propose the splitting of western languages such as English and German into sub-words or compounds. In this paper, we try to address this OOV issue and improve the NMT adequacy with a harder language Chinese whose characters are even more sophisticated in composition. We integrate the Chinese radicals into the NMT model with different settings to address the unseen words challenge in Chinese to English translation. On the other hand, this also can be considered as semantic part of the MT system since the Chinese radicals usually carry the essential meaning of the words they are constructed in. Meaningful radicals and new characters can be integrated into the NMT systems with our models. We use an attention-based NMT system as a strong baseline system. The experiments on standard Chinese-to-English NIST translation shared task data 2006 and 2008 show that our designed models outperform the baseline model in a wide range of state-of-the-art evaluation metrics including LEPOR, BEER, and CharacTER, in addition to BLEU and NIST scores, especially on the adequacy-level translation. We also have some interesting findings from the results of our various experiment settings about the performance of words and characters in Chinese NMT, which is different with other languages. For instance, the fully character level NMT may perform well or the state of the art in some other languages as researchers demonstrated recently, however, in the Chinese NMT model, word boundary knowledge is important for the model learning.

arXiv:1805.03750

Neural Machine Translation Decoding with Terminology Constraints

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.

arXiv:1805.03620

On the Limitations of Unsupervised Bilingual Dictionary Induction

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised alignment of word embedding spaces for bilingual dictionary induction (Conneau et al., 2018), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologically rich languages that are not dependent marking, when monolingual corpora from different domains or different embedding algorithms are used. We show that a simple trick, exploiting a weak supervision signal from identical words, enables more robust induction, and establish a near-perfect correlation between unsupervised bilingual dictionary induction performance and a previously unexplored graph similarity metric.

arXiv:1711.05380

Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and their possible target counterparts are not explicitly stored. Source and target words are at the two ends of a long information processing procedure, mediated by hidden states at both the source encoding and the target decoding phases. This makes it possible that a source word is incorrectly translated into a target word that is not any of its admissible equivalent counterparts in the target language. In this paper, we seek to somewhat shorten the distance between source and target words in that procedure, and thus strengthen their association, by means of a method we term bridging source and target word embeddings. We experiment with three strategies: (1) a source-side bridging model, where source word embeddings are moved one step closer to the output target sequence; (2) a target-side bridging model, which explores the more relevant source word embeddings for the prediction of the target sequence; and (3) a direct bridging model, which directly connects source and target word embeddings seeking to minimize errors in the translation of ones by the others. Experiments and analysis presented in this paper demonstrate that the proposed bridging models are able to significantly improve quality of both sentence translation, in general, and alignment and translation of individual source words with target words, in particular.

arXiv:1805.04453

Bootstrapping Multilingual Intent Models via Machine Translation for Dialog Automation

With the resurgence of chat-based dialog systems in consumer and enterprise applications, there has been much success in developing data-driven and rule-based natural language models to understand human intent. Since these models require large amounts of data and in-domain knowledge, expanding an equivalent service into new markets is disrupted by language barriers that inhibit dialog automation. This paper presents a user study to evaluate the utility of out-of-the-box machine translation technology to (1) rapidly bootstrap multilingual spoken dialog systems and (2) enable existing human analysts to understand foreign language utterances. We additionally evaluate the utility of machine translation in human assisted environments, where a portion of the traffic is processed by analysts. In English->Spanish experiments, we observe a high potential for dialog automation, as well as the potential for human analysts to process foreign language utterances with high accuracy.

arXiv:1805.04237

Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach

Neural machine translation requires large amounts of parallel training text to learn a reasonable-quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is not available. In this paper, we use monolingual linguistic resources in the source side to address this challenging problem based on a multi-task learning approach. More specifically, we scaffold the machine translation task on auxiliary tasks including semantic parsing, syntactic parsing, and named-entity recognition. This effectively injects semantic and/or syntactic knowledge into the translation model, which would otherwise require a large amount of training bitext. We empirically evaluate and show the effectiveness of our multi-task learning approach on three translation tasks: English-to-French, English-to-Farsi, and English-to-Vietnamese.

arXiv:1805.04218

Deep RNNs Encode Soft Hierarchical Syntax

We present a set of experiments to demonstrate that deep recurrent neural networks (RNNs) learn internal representations that capture soft hierarchical notions of syntax from highly varied supervision. We consider four syntax tasks at different depths of the parse tree; for each word, we predict its part of speech as well as the first (parent), second (grandparent) and third level (great-grandparent) constituent labels that appear above it. These predictions are made from representations produced at different depths in networks that are pretrained with one of four objectives: dependency parsing, semantic role labeling, machine translation, or language modeling. In every case, we find a correspondence between network depth and syntactic depth, suggesting that a soft syntactic hierarchy emerges. This effect is robust across all conditions, indicating that the models encode significant amounts of syntax even in the absence of an explicit syntactic training supervision.

arXiv:1805.04185공식 코드 · Papers with Code

Deep Neural Machine Translation with Weakly-Recurrent Units

Recurrent neural networks (RNNs) have represented for years the state of the art in neural machine translation. Recently, new architectures have been proposed, which can leverage parallel computation on GPUs better than classical RNNs. Faster training and inference combined with different sequence-to-sequence modeling also lead to performance improvements. While the new models completely depart from the original recurrent architecture, we decided to investigate how to make RNNs more efficient. In this work, we propose a new recurrent NMT architecture, called Simple Recurrent NMT, built on a class of fast and weakly-recurrent units that use layer normalization and multiple attentions. Our experiments on the WMT14 English-to-German and WMT16 English-Romanian benchmarks show that our model represents a valid alternative to LSTMs, as it can achieve better results at a significantly lower computational cost.

arXiv:1805.04016공식 코드 · Papers with Code

Automatic Estimation of Simultaneous Interpreter Performance

Simultaneous interpretation, translation of the spoken word in real-time, is both highly challenging and physically demanding. Methods to predict interpreter confidence and the adequacy of the interpreted message have a number of potential applications, such as in computer-assisted interpretation interfaces or pedagogical tools. We propose the task of predicting simultaneous interpreter performance by building on existing methodology for quality estimation (QE) of machine translation output. In experiments over five settings in three language pairs, we extend a QE pipeline to estimate interpreter performance (as approximated by the METEOR evaluation metric) and propose novel features reflecting interpretation strategy and evaluation measures that further improve prediction accuracy.

arXiv:1805.00456

Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT

We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.

arXiv:1805.04871공식 코드 · Papers with Code

Bag-of-Words as Target for Neural Machine Translation

A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the incorrect sentences in the training stage. Since most of the correct translations for one sentence share the similar bag-of-words, it is possible to distinguish the correct translations from the incorrect ones by the bag-of-words. In this paper, we propose an approach that uses both the sentences and the bag-of-words as targets in the training stage, in order to encourage the model to generate the potentially correct sentences that are not appeared in the training set. We evaluate our model on a Chinese-English translation dataset, and experiments show our model outperforms the strong baselines by the BLEU score of 4.55.

arXiv:1805.04813

Triangular Architecture for Rare Language Translation

Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data $(Y,Z)$ (may be small) and $(X,Y)$ (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, $Z$ is taken as the intermediate latent variable, and translation models of $Z$ are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of $(X,Y)$. Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.

arXiv:1805.05095

Bianet: A Parallel News Corpus in Turkish, Kurdish and English

We present a new open-source parallel corpus consisting of news articles collected from the Bianet magazine, an online newspaper that publishes Turkish news, often along with their translations in English and Kurdish. In this paper, we describe the collection process of the corpus and its statistical properties. We validate the benefit of using the Bianet corpus by evaluating bilingual and multilingual neural machine translation models in English-Turkish and English-Kurdish directions.

arXiv:1805.05062공식 코드 · Papers with Code

Token-level and sequence-level loss smoothing for RNN language models

Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match the ground truth as equally poor, ignoring the structure of the output space. Second, it suffers from "exposure bias": during training tokens are predicted given ground-truth sequences, while at test time prediction is conditioned on generated output sequences. To overcome these limitations we build upon the recent reward augmented maximum likelihood approach \ie sequence-level smoothing that encourages the model to predict sentences close to the ground truth according to a given performance metric. We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach. Our experiments on two different tasks, image captioning and machine translation, show that token-level and sequence-level loss smoothing are complementary, and significantly improve results.

arXiv:1805.06536

Are BLEU and Meaning Representation in Opposition?

One of possible ways of obtaining continuous-space sentence representations is by training neural machine translation (NMT) systems. The recent attention mechanism however removes the single point in the neural network from which the source sentence representation can be extracted. We propose several variations of the attentive NMT architecture bringing this meeting point back. Empirical evaluation suggests that the better the translation quality, the worse the learned sentence representations serve in a wide range of classification and similarity tasks.

arXiv:1805.06522

Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation

This paper provides a comparative analysis of the performance of four state-of-the-art distributional semantic models (DSMs) over 11 languages, contrasting the native language-specific models with the use of machine translation over English-based DSMs. The experimental results show that there is a significant improvement (average of 16.7% for the Spearman correlation) by using state-of-the-art machine translation approaches. The results also show that the benefit of using the most informative corpus outweighs the possible errors introduced by the machine translation. For all languages, the combination of machine translation over the Word2Vec English distributional model provided the best results consistently (average Spearman correlation of 0.68).