PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1608.01910

Resolving Out-of-Vocabulary Words with Bilingual Embeddings in Machine Translation

Out-of-vocabulary words account for a large proportion of errors in machine translation systems, especially when the system is used on a different domain than the one where it was trained. In order to alleviate the problem, we propose to use a log-bilinear softmax-based model for vocabulary expansion, such that given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language. Our model uses only word embeddings trained on significantly large unlabelled monolingual corpora and trains over a fairly small, word-to-word bilingual dictionary. We input this probabilistic list into a standard phrase-based statistical machine translation system and obtain consistent improvements in translation quality on the English-Spanish language pair. Especially, we get an improvement of 3.9 BLEU points when tested over an out-of-domain test set.

arXiv:1604.04661

Parallelizing Word2Vec in Shared and Distributed Memory

Word2Vec is a widely used algorithm for extracting low-dimensional vector representations of words. It generated considerable excitement in the machine learning and natural language processing (NLP) communities recently due to its exceptional performance in many NLP applications such as named entity recognition, sentiment analysis, machine translation and question answering. State-of-the-art algorithms including those by Mikolov et al. have been parallelized for multi-core CPU architectures but are based on vector-vector operations that are memory-bandwidth intensive and do not efficiently use computational resources. In this paper, we improve reuse of various data structures in the algorithm through the use of minibatching, hence allowing us to express the problem using matrix multiply operations. We also explore different techniques to distribute word2vec computation across nodes in a compute cluster, and demonstrate good strong scalability up to 32 nodes. In combination, these techniques allow us to scale up the computation near linearly across cores and nodes, and process hundreds of millions of words per second, which is the fastest word2vec implementation to the best of our knowledge.

arXiv:1601.04811공식 코드 · Papers with Code

Modeling Coverage for Neural Machine Translation

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words. Experiments show that the proposed approach significantly improves both translation quality and alignment quality over standard attention-based NMT.

arXiv:1608.03639

Faster Training of Very Deep Networks Via p-Norm Gates

A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforward models such as Residual Nets and Highway Networks. This enables learning in very deep networks with hundred layers and helps achieve record-breaking results in vision (e.g., ImageNet with Residual Nets) and NLP (e.g., machine translation with GRU). However, there is limited work in analysing the role of gating in the learning process. In this paper, we propose a flexible $p$-norm gating scheme, which allows user-controllable flow and as a consequence, improve the learning speed. This scheme subsumes other existing gating schemes, including those in GRU, Highway Networks and Residual Nets as special cases. Experiments on large sequence and vector datasets demonstrate that the proposed gating scheme helps improve the learning speed significantly without extra overhead.

arXiv:1608.02927

Temporal Attention Model for Neural Machine Translation

Attention-based Neural Machine Translation (NMT) models suffer from attention deficiency issues as has been observed in recent research. We propose a novel mechanism to address some of these limitations and improve the NMT attention. Specifically, our approach memorizes the alignments temporally (within each sentence) and modulates the attention with the accumulated temporal memory, as the decoder generates the candidate translation. We compare our approach against the baseline NMT model and two other related approaches that address this issue either explicitly or implicitly. Large-scale experiments on two language pairs show that our approach achieves better and robust gains over the baseline and related NMT approaches. Our model further outperforms strong SMT baselines in some settings even without using ensembles.

arXiv:1605.09186

Does Multimodality Help Human and Machine for Translation and Image Captioning?

This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate the usefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.

arXiv:1608.04738공식 코드 · Papers with Code

An Efficient Character-Level Neural Machine Translation

Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to the existing state-of-the-art phrase-based systems on the task of English-to-French translation. However, the use of large vocabulary becomes the bottleneck in both training and improving the performance. In this paper, we propose an efficient architecture to train a deep character-level neural machine translation by introducing a decimator and an interpolator. The decimator is used to sample the source sequence before encoding while the interpolator is used to resample after decoding. Such a deep model has two major advantages. It avoids the large vocabulary issue radically; at the same time, it is much faster and more memory-efficient in training than conventional character-based models. More interestingly, our model is able to translate the misspelled word like human beings.

arXiv:1608.05554

Learning to Start for Sequence to Sequence Architecture

The sequence to sequence architecture is widely used in the response generation and neural machine translation to model the potential relationship between two sentences. It typically consists of two parts: an encoder that reads from the source sentence and a decoder that generates the target sentence word by word according to the encoder's output and the last generated word. However, it faces to the cold start problem when generating the first word as there is no previous word to refer. Existing work mainly use a special start symbol </s>to generate the first word. An obvious drawback of these work is that there is not a learnable relationship between words and the start symbol. Furthermore, it may lead to the error accumulation for decoding when the first word is incorrectly generated. In this paper, we proposed a novel approach to learning to generate the first word in the sequence to sequence architecture rather than using the start symbol. Experimental results on the task of response generation of short text conversation show that the proposed approach outperforms the state-of-the-art approach in both of the automatic and manual evaluations.

arXiv:1603.08148

Pointing the Unknown Words

The problem of rare and unknown words is an important issue that can potentially influence the performance of many NLP systems, including both the traditional count-based and the deep learning models. We propose a novel way to deal with the rare and unseen words for the neural network models using attention. Our model uses two softmax layers in order to predict the next word in conditional language models: one predicts the location of a word in the source sentence, and the other predicts a word in the shortlist vocabulary. At each time-step, the decision of which softmax layer to use choose adaptively made by an MLP which is conditioned on the context.~We motivate our work from a psychological evidence that humans naturally have a tendency to point towards objects in the context or the environment when the name of an object is not known.~We observe improvements on two tasks, neural machine translation on the Europarl English to French parallel corpora and text summarization on the Gigaword dataset using our proposed model.

arXiv:1605.03148

Coverage Embedding Models for Neural Machine Translation

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.

arXiv:1609.01188

Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation

We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this is done using length-based alignment, but for movie subtitles, there is also time information. Here we exploit this information to develop an original algorithm that outperforms the current best subtitle alignment tool, subalign. The evaluation results show that adding our bi-text to the IWSLT training bi-text yields an improvement of over two BLEU points absolute.

arXiv:1609.03205

Unsupervised Identification of Translationese

Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine translation. However, it has been suggested that the accuracy of translation detection deteriorates when the classifier is evaluated outside the domain it was trained on. We show that this is indeed the case, in a variety of evaluation scenarios. We then show that unsupervised classification is highly accurate on this task. We suggest a method for determining the correct labels of the clustering outcomes, and then use the labels for voting, improving the accuracy even further. Moreover, we suggest a simple method for clustering in the challenging case of mixed-domain datasets, in spite of the dominance of domain-related features over translation-related ones. The result is an effective, fully-unsupervised method for distinguishing between original and translated texts that can be applied to new domains with reasonable accuracy.

arXiv:1609.04186

Neural Machine Translation with Supervised Attention

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in aligment accuracy. In this paper, we analyze and explain this issue from the point view of re- ordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the super- vised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

arXiv:1609.03976

Multimodal Attention for Neural Machine Translation

The attention mechanism is an important part of the neural machine translation (NMT) where it was reported to produce richer source representation compared to fixed-length encoding sequence-to-sequence models. Recently, the effectiveness of attention has also been explored in the context of image captioning. In this work, we assess the feasibility of a multimodal attention mechanism that simultaneously focus over an image and its natural language description for generating a description in another language. We train several variants of our proposed attention mechanism on the Multi30k multilingual image captioning dataset. We show that a dedicated attention for each modality achieves up to 1.6 points in BLEU and METEOR compared to a textual NMT baseline.

arXiv:1609.03376

Morphological Constraints for Phrase Pivot Statistical Machine Translation

The lack of parallel data for many language pairs is an important challenge to statistical machine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target languages. Although pivoting is a robust technique, it introduces some low quality translations especially when a poor morphology language is used as the pivot between rich morphology languages. In this paper, we examine the use of synchronous morphology constraint features to improve the quality of phrase pivot SMT. We compare hand-crafted constraints to those learned from limited parallel data between source and target languages. The learned morphology constraints are based on projected align- ments between the source and target phrases in the pivot phrase table. We show positive results on Hebrew-Arabic SMT (pivoting on English). We get 1.5 BLEU points over a phrase pivot baseline and 0.8 BLEU points over a system combination baseline with a direct model built from parallel data.

arXiv:1609.04621

Factored Neural Machine Translation

We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in MT, namely dealing with a large target language vocabulary and the out of vocabulary (OOV) words. By the means of factors, we are able to handle larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). In addition, we can produce new words that are not in the vocabulary. We use a morphological analyser to get a factored representation of each word (lemmas, Part of Speech tag, tense, person, gender and number). We have extended the NMT approach with attention mechanism in order to have two different outputs, one for the lemmas and the other for the rest of the factors. The final translation is built using some \textit{a priori} linguistic information. We compare our extension with a word-based NMT system. The experiments, performed on the IWSLT'15 dataset translating from English to French, show that while the performance do not always increase, the system can manage a much larger vocabulary and consistently reduce the OOV rate. We observe up to 2% BLEU point improvement in a simulated out of domain translation setup.

arXiv:1609.06490

One Sentence One Model for Neural Machine Translation

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is used to translate all the test sentences. We argue that the general fixed network cannot best fit the specific test sentences. In this paper, we propose the dynamic NMT which learns a general network as usual, and then fine-tunes the network for each test sentence. The fine-tune work is done on a small set of the bilingual training data that is obtained through similarity search according to the test sentence. Extensive experiments demonstrate that this method can significantly improve the translation performance, especially when highly similar sentences are available.

arXiv:1606.07947공식 코드 · Papers with Code

Sequence-Level Knowledge Distillation

Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches. However to reach competitive performance, NMT models need to be exceedingly large. In this paper we consider applying knowledge distillation approaches (Bucila et al., 2006; Hinton et al., 2015) that have proven successful for reducing the size of neural models in other domains to the problem of NMT. We demonstrate that standard knowledge distillation applied to word-level prediction can be effective for NMT, and also introduce two novel sequence-level versions of knowledge distillation that further improve performance, and somewhat surprisingly, seem to eliminate the need for beam search (even when applied on the original teacher model). Our best student model runs 10 times faster than its state-of-the-art teacher with little loss in performance. It is also significantly better than a baseline model trained without knowledge distillation: by 4.2/1.7 BLEU with greedy decoding/beam search. Applying weight pruning on top of knowledge distillation results in a student model that has 13 times fewer parameters than the original teacher model, with a decrease of 0.4 BLEU.

arXiv:1609.07701

Large-Scale Machine Translation between Arabic and Hebrew: Available Corpora and Initial Results

Machine translation between Arabic and Hebrew has so far been limited by a lack of parallel corpora, despite the political and cultural importance of this language pair. Previous work relied on manually-crafted grammars or pivoting via English, both of which are unsatisfactory for building a scalable and accurate MT system. In this work, we compare standard phrase-based and neural systems on Arabic-Hebrew translation. We experiment with tokenization by external tools and sub-word modeling by character-level neural models, and show that both methods lead to improved translation performance, with a small advantage to the neural models.

arXiv:1607.00030공식 코드 · Papers with Code

HUME: Human UCCA-Based Evaluation of Machine Translation

Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales. However, these provide no insight into possible errors, and do not scale well with sentence length. We argue for a semantics-based evaluation, which captures what meaning components are retained in the MT output, thus providing a more fine-grained analysis of translation quality, and enabling the construction and tuning of semantics-based MT. We present a novel human semantic evaluation measure, Human UCCA-based MT Evaluation (HUME), building on the UCCA semantic representation scheme. HUME covers a wider range of semantic phenomena than previous methods and does not rely on semantic annotation of the potentially garbled MT output. We experiment with four language pairs, demonstrating HUME's broad applicability, and report good inter-annotator agreement rates and correlation with human adequacy scores.