Searcharxiv⌕ Search

arXiv subjects

Masao Utiyama

Publications and source records attributed to Masao Utiyama.

51 records · Page 3Linked to original sources
arXiv2019

Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured difference between the training costs of two iterations. Further, in each epoch, a certain percentage of sentences are dynamically sampled according to their weights. Empirical results based on the NIST Chinese-to-English and the WMT English-to-German tasks depict that the proposed method can significantly accelerate the NMT training and improve the NMT performance.

cs.CL↗
arXiv2019

Syntax-Directed Attention for Neural Machine Translation

Attention mechanism, including global attention and local attention, plays a key role in neural machine translation (NMT). Global attention attends to all source words for word prediction. In comparison, local attention selectively looks at fixed-window source words. However, alignment weights for the current target word often decrease to the left and right by linear distance centering on the aligned source position and neglect syntax-directed distance constraints. In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction. Moreover, we further propose a double context NMT architecture, which consists of a global context vector and a syntax-directed context vector over the global attention, to provide more translation performance for NMT from source representation. The experiments on the large-scale Chinese-to-English and English-to-Germen translation tasks show that the proposed approach achieves a substantial and significant improvement over the baseline system.

cs.CL↗
arXiv2019

Hybrid Data-Model Parallel Training for Sequence-to-Sequence Recurrent Neural Network Machine Translation

Reduction of training time is an important issue in many tasks like patent translation involving neural networks. Data parallelism and model parallelism are two common approaches for reducing training time using multiple graphics processing units (GPUs) on one machine. In this paper, we propose a hybrid data-model parallel approach for sequence-to-sequence (Seq2Seq) recurrent neural network (RNN) machine translation. We apply a model parallel approach to the RNN encoder-decoder part of the Seq2Seq model and a data parallel approach to the attention-softmax part of the model. We achieved a speed-up of 4.13 to 4.20 times when using 4 GPUs compared with the training speed when using 1 GPU without affecting machine translation accuracy as measured in terms of BLEU scores.

cs.DC↗
arXiv2018

Exploring Recombination for Efficient Decoding of Neural Machine Translation

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently no matter how similar they are. However, this might be inefficient since some partial hypotheses can contain only local differences that will not influence future predictions. In this work, we introduce recombination in NMT decoding based on the concept of the "equivalence" of partial hypotheses. Heuristically, we use a simple $n$-gram suffix based equivalence function and adapt it into beam search decoding. Through experiments on large-scale Chinese-to-English and English-to-Germen translation tasks, we show that the proposed method can obtain similar translation quality with a smaller beam size, making NMT decoding more efficient.

cs.CL↗
arXiv2018

NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task

This paper presents the NICT's participation to the WMT18 shared news translation task. We participated in the eight translation directions of four language pairs: Estonian-English, Finnish-English, Turkish-English and Chinese-English. For each translation direction, we prepared state-of-the-art statistical (SMT) and neural (NMT) machine translation systems. Our NMT systems were trained with the transformer architecture using the provided parallel data enlarged with a large quantity of back-translated monolingual data that we generated with a new incremental training framework. Our primary submissions to the task are the result of a simple combination of our SMT and NMT systems. Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.

cs.CL↗
arXiv2018

NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filtering Task

This paper presents the NICT's participation in the WMT18 shared parallel corpus filtering task. The organizers provided 1 billion words German-English corpus crawled from the web as part of the Paracrawl project. This corpus is too noisy to build an acceptable neural machine translation (NMT) system. Using the clean data of the WMT18 shared news translation task, we designed several features and trained a classifier to score each sentence pairs in the noisy data. Finally, we sampled 100 million and 10 million words and built corresponding NMT systems. Empirical results show that our NMT systems trained on sampled data achieve promising performance.

cs.CL↗
arXiv2018

CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++

This paper presents an open-source neural machine translation toolkit named CytonMT (https://github.com/arthurxlw/cytonMt). The toolkit is built from scratch only using C++ and NVIDIA's GPU-accelerated libraries. The toolkit features training efficiency, code simplicity and translation quality. Benchmarks show that CytonMT accelerates the training speed by 64.5% to 110.8% on neural networks of various sizes, and achieves competitive translation quality.

cs.CL↗
arXiv2018

Guiding Neural Machine Translation with Retrieved Translation Pieces

One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective method for recalling previously seen translation examples and incorporating them into the NMT decoding process. Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect $n$-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "translation pieces". We compute pseudo-probabilities for each retrieved sentence based on similarities between the input sentence and the retrieved source sentences, and use these to weight the retrieved translation pieces. Finally, an existing NMT model is used to translate the input sentence, with an additional bonus given to outputs that contain the collected translation pieces. We show our method improves NMT translation results up to 6 BLEU points on three narrow domain translation tasks where repetitiveness of the target sentences is particularly salient. It also causes little increase in the translation time, and compares favorably to another alternative retrieval-based method with respect to accuracy, speed, and simplicity of implementation.

cs.CL↗
arXiv2017

Improving Neural Machine Translation through Phrase-based Forced Decoding

Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using this cost to rerank the n-best NMT outputs. The main challenge in implementing this approach is that NMT outputs may not be in the search space of the standard phrase-based decoding algorithm, because the search space of phrase-based SMT is limited by the phrase-based translation rule table. We propose a soft forced decoding algorithm, which can always successfully find a decoding path for any NMT output. We show that using the forced decoding cost to rerank the NMT outputs can successfully improve translation quality on four different language pairs.

cs.CL↗
arXiv2016

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.

cs.CL↗
arXiv2016

A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique

Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The proposed method is evaluated on bilingual lexicon translation tasks and empirical results show that bilingual sense embedding methods outperform existing bilingual word embedding methods.

cs.CL↗
arXiv2016

Connecting Phrase based Statistical Machine Translation Adaptation

Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains with the original corpus can indeed enhance SMT performance directly. Most of the existing adaptation methods focus on sentence selection. In comparison, phrase is a smaller and more fine grained unit for data selection, therefore we propose a straightforward and efficient connecting phrase based adaptation method, which is applied to both bilingual phrase pair and monolingual n-gram adaptation. The proposed method is evaluated on IWSLT/NIST data sets, and the results show that phrase based SMT performance are significantly improved (up to +1.6 in comparison with phrase based SMT baseline system and +0.9 in comparison with existing methods).

cs.CL↗
arXiv2001

CRL at Ntcir2

We have developed systems of two types for NTCIR2. One is an enhenced version of the system we developed for NTCIR1 and IREX. It submitted retrieval results for JJ and CC tasks. A variety of parameters were tried with the system. It used such characteristics of newspapers as locational information in the CC tasks. The system got good results for both of the tasks. The other system is a portable system which avoids free parameters as much as possible. The system submitted retrieval results for JJ, JE, EE, EJ, and CC tasks. The system automatically determined the number of top documents and the weight of the original query used in automatic-feedback retrieval. It also determined relevant terms quite robustly. For EJ and JE tasks, it used document expansion to augment the initial queries. It achieved good results, except on the CC tasks.

cs.CL↗
arXiv2000

Japanese Probabilistic Information Retrieval Using Location and Category Information

Robertson's 2-poisson information retrieve model does not use location and category information. We constructed a framework using location and category information in a 2-poisson model. We submitted two systems based on this framework to the IREX contest, Japanese language information retrieval contest held in Japan in 1999. For precision in the A-judgement measure they scored 0.4926 and 0.4827, the highest values among the 15 teams and 22 systems that participated in the IREX contest. We describe our systems and the comparative experiments done when various parameters were changed. These experiments confirmed the effectiveness of using location and category information.

cs.CL↗