Bilingual LSA-based adaptation for statistical machine translation

We propose a novel approach to cross-lingual language model and translation lexicon adaptation for statistical machine translation (SMT) based on bilingual latent semantic analysis. Bilingual LSA enables latent topic distributions to be efficiently transferred across languages by enforcing a one-to-one topic correspondence during training. Using the proposed bilingual LSA framework, model adaptation can be performed by, first, inferring the topic posterior distribution of the source text and then applying the inferred distribution to an n-gram language model of the target language and translation lexicon via marginal adaptation. The background phrase table is enhanced with the additional phrase scores computed using the adapted translation lexicon. The proposed framework also features rapid bootstrapping of LSA models for new languages based on a source LSA model of another language. Our approach is evaluated on the Chinese–English MT06 test set using the medium-scale SMT system and the GALE SMT system measured in BLEU and NIST scores. Improvement in both scores is observed on both systems when the adapted language model and the adapted translation lexicon are applied individually. When the adapted language model and the adapted translation lexicon are applied simultaneously, the gain is additive. At the 95% confidence interval of the unadapted baseline system, the gain in both scores is statistically significant using the medium-scale SMT system, while the gain in the NIST score is statistically significant using the GALE SMT system.     

A syntactically informed reordering model for statistical machine translation

Word reordering is one of the challengeable problems of machine translation. It is an important factor of quality and efficiency of machine translation systems. In this paper, we introduce a novel reordering model based on an innovative structure, named, phrasal dependency tree. The phrasal dependency tree is a modern syntactic structure which is based on dependency relationships between contiguous non-syntactic phrases. The proposed model integrates syntactical and statistical information in the context of log-linear model aimed at dealing with the reordering problems. It benefits from phrase dependencies, translation directions (orientations) and translation discontinuity between translated phrases. In comparison with well-known and popular reordering models such as distortion, lexicalised and hierarchical models, the experimental study demonstrates the superiority of our model in terms of translation quality. Performance is evaluated for Persian → English and English → German translation tasks using Tehran parallel corpus and WMT07 benchmarks, respectively. The results report 1.54/1.7 and 1.98/3.01 point improvements over the baseline in terms of BLEU/TER metrics on Persian → English and German → English translation tasks, respectively. On average our model retrieved a significant impact on precision with comparable recall value with respect to the lexicalised and distortion models.     

统计机器翻译中翻译规则抽取

对齐短语是决定统计机器翻译系统质量的核心模块。提出基于短语结构树的层次短语模型,这是利用串-树模型的思想对层次短语模型的扩展。基于短语结构树的层次短语模型是在双语对齐短语的基础之上结合英语短语结构树抽取翻译规则,并利用启发式策略获得翻译规则的扩展句法标记。采用翻译规则的统计机器翻译系统在不同数据集上具有稳定的翻译结果,在训练集和测试集的平均BlEU评分高于短语模型和层次短语模型的BLEU评分。     

基于强化学习和机器翻译质量评估的中朝机器翻译研究

针对目前机器翻译模型存在的曝光偏差和译文多样性差的问题,提出一种基于强化学习和机器翻译质量评估的中朝神经机器翻译模型QR-Transformer.首先,在句子级别引入评价机制来指导模型预测不完全收敛于参考译文;其次,采用强化学习方法作为指导策略,实现模型在句子级别优化目标序列;最后,在训练过程中融入单语语料并进行多粒度数据预处理以缓解数据稀疏问题.实验表明,QR-Transformer有效提升了中朝神经机器翻译性能,与Transformer相比,中—朝语向BLEU值提升了5.39,QE分数降低了5.16,朝—中语向BLEU值提升了2.73,QE分数下降了2.82.     

N-Best句法知识增强的统计机器翻译预调序模型

源语言和目标语言的句法异构性对统计机器翻译（SMT）性能有重要影响。在基于短语的汉英统计机器翻译基础上,提出了一种基于N-best句法知识增强的源语言预调序方法。首先对源语言输入句子进行N-best句法分析,计算统计概率得到高可靠性子树结构,再根据词对齐信息从可靠性子树结构中抽取初始调序规则集。两种优化策略用于对初始规则集进行优化：基于中英文句法知识规则推导筛选和规则概率阈值控制机制。然后为减少短语内部调序,保证短语局部流利性,采用源语言短语翻译表为约束,使调序控制在短语块之间进行。最后根据获取的优化规则集和短语表约束条件对源语言端句子的句法分析树进行预调序。在基于NIST 2005和2008测试数据集上的汉英统计机器翻译实验结果表明,所提基于N-best句法知识增强的统计机器翻译预调序方法相对于基线系统,自动评价准则BLEU得分分别提高了0.68和0.83。     

Example-based machine translation: a review and commentary

In the last decade the dominant models of MT have been data-driven or corpus-based. Of the two main trends, statistical machine translation and example-based machine translation (EBMT), the latter is much less clearly defined. In a review of the recently published collection edited by Michael Carl and Andy Way, this essay surveys the basic processes, methods, main problems and tasks of EBMT, and attempts to provide a definition of the essence of EBMT in comparison with statistical MT and traditional rule-based MT. Recent Advances in Example-based Machine Translation. Edited by Michael Carl and Andy Way. Dordrecht: Kluwer Academic Publishers, 2003. xxxi, 482pp. (Text, Speech and Language Technology, vol. 21) ISBN: 1-4020-1400-7 (hardback), 1-4020-1401-5 (paperback).     

Pivot language approach for phrase-based statistical machine translation

This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language. To translate between languages L _s and L _t with limited bilingual resources, we bring in a third language, L _p , called the pivot language. For the language pairs L _s  − L _p and L _p  − L _t , there exist large bilingual corpora. Using only L _s  − L _p and L _p  − L _t bilingual corpora, we can build a translation model for L _s  − L _t . The advantage of this method lies in the fact that we can perform translation between L _s and L _t even if there is no bilingual corpus available for this language pair. Using BLEU as a metric, our pivot language approach significantly outperforms the standard model trained on a small bilingual corpus. Moreover, with a small L _s  − L _t bilingual corpus available, our method can further improve translation quality by using the additional L _s  − L _p and L _p  − L _t bilingual corpora.     

句法调序的统计机器翻译方法研究

为解决基于短语统计机器翻译存在的调序能力不足的问题,尝试利用句法分析器对基于短语统计机器翻译的输入汉语句子进行句法分析,然后利用转换器进行调序操作,并对部分类型短语进行预先翻译,然后再利用基于短语统计机器翻译的解码器进行翻译。重点测试了汉语中“的”字引导的复杂定语调序、介词短语、特定搭配短语、方位词短语的调序及预翻译产生的效果。实验结果表明,这些调序及预翻译操作可以显著地提高基于短语的统计机器翻译的英文译文结果的BLEU值。     

基于短语的汉蒙统计机器翻译研究

基于短语的统计机器翻译是当前统计机器翻译的主流方法。研究了利用现有技术和资源搭建一个基于短语的汉蒙机器翻译系统的方法,并且构建了一个汉蒙机器翻译的自动评价平台,在此基础上利用词典和蒙古语形态学信息来提高了翻译系统的性能。     

Example-based machine translation based on tree–string correspondence and statistical generation

This paper describes an example-based machine translation (EBMT) method based on tree–string correspondence (TSC) and statistical generation. In this method, the translation example is represented as a TSC, which is a triple consisting of a parse tree in the source language, a string in the target language, and the correspondence between the leaf node of the source-language tree and the substring of the target-language string. For an input sentence to be translated, it is first parsed into a tree. Then the TSC forest which best matches the input tree is searched for. Finally the translation is generated using a statistical generation model to combine the target-language strings of the TSCs. The generation model consists of three features: the semantic similarity between the tree in the TSC and the input tree, the translation probability of translating the source word into the target word, and the language-model probability for the target-language string. Based on the above method, we build an English-to-Chinese MT system. Experimental results indicate that the performance of our system is comparable with phrase-based statistical MT systems.     

基于短语统计翻译的汉维机器翻译系统

描述了一种基于短语统计翻译的汉维机器翻译系统。首先使用汉维语料进行训练,得到语言模型和翻译模型;再利用训练好的模型对源语句进行解码,以得到最佳的翻译语句。解码的核心算法是柱搜索（beam search）算法。其中维文语料使用的是拉丁维文。实验结果表明,基于短语的统计机器翻译方法可以快速有效地构建一个汉维机器翻译平台。     

双语词典在统计机器翻译中的应用

在当前的基于统计的翻译方法中,双语语料库的规模、词对齐的准确率对于翻译系统的性能有很大的影响。虽然大规模语料库可以改善词语对齐的准确度,提高系统的性能,但同时会以增加系统的负载为代价,因此目前对于统计机器翻译方法的研究在使用大规模语料库的基础上,同时寻求其他可以提高系统性能的方法。针对以上问题,提出一种把双语词典应用在统计机器翻译中的方法,不仅优化了词对齐的准确率,而且得出质量更高的翻译结果,在一定程度上缓解了数据稀疏问题。     

半监督多示例核

在多示例学习中引入利用未标记示例的机制,能降低训练的成本并提高学习器的泛化能力。当前半监督多示例学习算法大部分是基于对包中的每一个示例进行标记,把多示例学习转化为一个单示例半监督学习问题。考虑到包的类标记由包中示例及包的结构决定,提出一种直接在包层次上进行半监督学习的多示例学习算法。通过定义多示例核,利用所有包(有标记和未标记)计算包层次的图拉普拉斯矩阵,作为优化目标中的光滑性惩罚项。在多示例核所张成的RKHS空间中寻找最优解被归结为确定一个经过未标记数据修改的多示例核函数,它能直接用在经典的核学习方法上。在实验数据集上对算法进行了测试,并和已有的算法进行了比较。实验结果表明,基于半监督多示例核的算法能够使用更少量的训练数据而达到与监督学习算法同样的精度,在有标记数据集相同的情况下利用未标记数据能有效地提高学习器的泛化能力。     

一种基于短语统计机器翻译的高效柱搜索解码器

描述了一种基于短语统计机器翻译的柱搜索解码器。搜索算法的效率是解码的关键,基于传统的柱搜索解码算法,提出了提高搜索效率的改进措施：动态剪枝策略改进了原来固定地剪枝对搜索当前情形反应不足的问题,提高了剪枝精度;预剪枝策略限制了较差的扩展,减少了不必要的扩展,提高了搜索速度;在研究了当前主要位置重排限制的基础上,提出了一种快速位置重排限制策略,加快了位置重排时的解码速度。此外,针对领域术语翻译唯一性问题提出了专门处理方法以提高翻译的准确度。分析对比实验结果,证明了算法的有效性。     

Novel algorithm machine translation for language translation tool

Fuzzy matching techniques are the presently used methods in translating the words. Neural machine translation and statistical machine translation are the methods used in MT. In machine translator tool, the strategy employed for translation needs to handle large amount of datasets and therefore the performance in retrieving correct matching output can be affected. In order to improve the matching score of MT, the advanced techniques can be presented by modifying the existing fuzzy based translator and neural machine translator. The conventional process of modifying architectures and encoding schemes are tedious process. Similarly, the preprocessing of datasets also involves more time consumption and memory utilization. In this article, a new spider web based searching enhanced translation is presented to be employed with the neural machine translator. The proposed scheme enables deep searching of available dataset to detect the accurate matching result. In addition, the quality of translation is improved by presenting an optimal selection scheme for using the sentence matches in source augmentation. The matches retrieved using various matching scores are applied to an optimization algorithm. The source augmentation using optimal retrieved matches increases the translation quality. Further, the selection of optimal match combination helps to reduce time requirement, since it is not necessary to test all retrieved matches in finding target sentence. The performance of translation is validated by measuring the quality of translation using BLEU and METEOR scores. These two scores can be achieved for the TA-EN language pairs in different configurations of about 92% and 86%, correspondingly. The results are evaluated and compared with other available NMT methods to validate the work.     

On the use of different loss functions in statistical pattern recognition applied to machine translation

In pattern recognition, an elegant and powerful way to deal with classification problems is based on the minimisation of the classification risk. The risk function is defined in terms of loss functions that measure the penalty for wrong decisions. However, in practice a trivial loss function is usually adopted (the so-called 0–1 loss function) that do no make the most of this framework. This work is focused on the study of different loss functions, and specially on those loss functions that do not depend on the class proposed by the system. Loss functions of this kind have allowed us to theoretically explain heuristics that are successfully used with very complex pattern recognition problem, such as (statistical) machine translation. A comparative experimental work has also been carried out to compare different proposals of loss functions in the practical scenario of machine translation.     

Variational multimodal machine translation with underlying semantic alignment

Capturing the underlying semantic relationships of sentences is helpful for machine translation. Variational neural machine translation approaches provide an effective way to model the uncertain underlying semantics in languages by introducing latent variables. Multitask learning is applied in multimodal machine translation to integrate multimodal data. However, these approaches usually lack a strong interpretation in utilizing out-of-text information in machine translation tasks. In this paper, we propose a novel architecture-free multimodal translation model, called variational multimodal machine translation (VMMT), under the variational framework which can model the uncertainty in languages caused by ambiguity through utilizing visual and textual information. In addition, the proposed model can eliminate the discrepancy between training and prediction in the existing variational translation models by constructing encoders only relying on source data. More importantly, the proposed multimodal translation model is designed as multitask learning in which the shared semantic representation for different modes is learned and the gap among semantic representation from various modes is reduced by incorporating additional constraints. Moreover, the information bottleneck theory is adopted in our variational encoder–decoder model, which helps the encoder to filter redundancy and the decoder to concentrate on useful information. Experiments on multimodal machine translation demonstrate that the proposed model is competitive.     

Dependency treelet translation: the convergence of statistical and example-based machine-translation?

We describe a novel approach to MT that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed decoder and reordering model based on the source dependency tree, in combination with conventional SMT models to incorporate the power of phrasal SMT with the linguistic generality available in a parser. We show that this approach significantly outperforms a leading string-based Phrasal SMT decoder and an EBMT system. We present results from two radically different language pairs, and investigate the sensitivity of this approach to parse quality by using two distinct parsers and oracle experiments. We also validate our automated bleu scores with a small human evaluation.