Improved language modeling for statistical machine translation

In this paper, we present our work on a case study between statistical machine translation (SMT) and rule-based machine translation (RBMT) systems on English-Indian language and Indian to Indian language perspective. Main objective of our study is to make a five-way performance comparison: such as, (a) SMT and RBMT; (b) SMT on English–Indian language; (c) RBMT on English–Indian language; (d) SMT on Indian to Indian language perspective; (e) RBMT on Indian to Indian language perspective. Through a detailed analysis, we describe the rule-based and the statistical machine translation system developments and its evaluations. Further, with a detailed error analysis, we point out the relative strengths and weaknesses of both the systems. The observations based on our study are: (a) SMT systems outperform RBMT; (b) In the case of SMT: English to Indian language MT systems perform better than Indian to English language MT systems; (c) In the case of RBMT: English to Indian language MT systems perform better than Indian to English language MT systems; (d) SMT systems perform better for Indian to Indian language MT systems compared to RBMT. Effectively, we shall see that even with a small amount of training corpus SMT system has many advantages for high-quality domain-specific machine translation over that of a rule-based counterpart.

A simplification–translation–restoration framework for domain adaptation in statistical machine translation: A case study in medical record translation

We report insights from translating Spanish conversational telephone speech into English text by cascading an automatic speech recognition (ASR) system with a statistical machine translation (SMT) system. The key new insight is that the informal register of conversational speech is a greater challenge for ASR than for SMT: the BLEU score for translating the reference transcript is 64%, but drops to 32% for translating automatic transcripts, whose word error rate (WER) is 40%. Several strategies are examined to mitigate the impact of ASR errors on the SMT output: (i) providing the ASR lattice, instead of the 1-best output, as input to the SMT system, (ii) training the SMT system on Spanish ASR output paired with English text, instead of Spanish reference transcripts, and (iii) improving the core ASR system. Each leads to consistent and complementary improvements in the SMT output. Compared to translating the 1-best output of an ASR system with 40% WER using an SMT system trained on Spanish reference transcripts, translating the output lattice of a better ASR system with 35% WER using an SMT system trained on ASR output improves BLEU from 32% to 38%.

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

In terms of language technology, Maithili is a resource-poor language. It is spoken in India and Nepal and is one of the 22 scheduled languages in India. Maithili has almost no language technology resource. English in India happens to be a dominant language in terms of content and usage. However, since more than 90% of Indians do not use English, a translation from English to Maithili becomes critical. An absence of basic tools in this language has affected resource creation of machine translation (MT). The present work discusses efforts for language technology resource (LTR) creation and divergence study for a statistical English-Maithili MT (EMMT) system. Creating any statistical MT (SMT) system requires sizeable parallel, aligned corpora for training and testing. Creating general-purpose source corpora for English language and creating translation equivalents with possible alignments require time and effort. The paper focuses on the data collection methods, cleaning, the size and structure of the text corpora, alignment and parallelization strategies, training, testing, and a study of divergence between the language pair.

Statistical machine translation systems usually compute the single sentence that has the highest probability according to the models that are trained on data. We describe a method for constructing a word graph to represent alternative hypotheses in an efficient way. The advantage is that these hypotheses can be rescored using a refined language or translation model. Results are presented on the German-English Verbmobil corpus.

In recent years, statistical machine translation has gained much attention. The phrase‐based statistical machine translation model has made significant advancement in translation quality over the word‐based model. In this paper, we attempt to apply the technique of proportional analogy to statistical machine translation systems. We propose a novel approach to apply proportional analogy to generate translations of unseen n‐grams from the phrase table for phrase‐based statistical machine translation. Experiments are conducted with two datasets of different sizes. We also investigate two methods to integrate n‐grams translations produced by proportional analogy into the state‐of‐the‐art statistical machine translation system, Moses.1The experimental results show that unseen n‐grams translations generated using the technique of proportional analogy are rewarding for statistical machine translation systems with small datasets. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Deep neural networks (DNNs) have provably enhanced the state-of-the-art natural language process (NLP) with their capability of feature learning and representation. As one of the more challenging NLP tasks, neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy and word coverage. It is therefore a promising direction to combine the advantages of both NMT and SMT. In this article, we propose a deep neural network--based system combination framework leveraging both minimum Bayes-risk decoding and multi-source NMT, which take as input the N-best outputs of NMT and SMT systems and produce the final translation. In particular, we apply the proposed model to both RNN and self-attention networks with different segmentation granularity. We verify our approach empirically through a series of experiments on resource-rich Chinese⇒English and low-resource English⇒Vietnamese translation tasks. Experimental results demonstrate the effectiveness and universality of our proposed approach, which significantly outperforms the conventional system combination methods and the best individual system output.

This paper presents example-based machine translation (MT) based on syntactic transfer, which selects the best translation by using models of statistical machine translation. Example-based MT sometimes generates invalid translations because it selects similar examples to the input sentence based only on source language similarity. The method proposed in this paper selects the best translation by using a language model and a translation model in the same manner as statistical MT, and it can improve MT quality over that of 'pure' example-based MT. A feature of this method is that the statistical models are applied after word re-ordering is achieved by syntactic transfer. This implies that MT quality is maintained even when we only apply a lexicon model as the translation model. In addition, translation speed is improved by bottom-up generation, which utilizes the tree structure that is output from the syntactic transfer.

There is no doubt that in the last couple of years corpus-based machine translation (CBMT) approaches have been in focus. Each of the CBMT approaches (statistical MT and example-based MT) has its advantages and disadvantages. Therefore, hybrid approaches have been developed. This paper presents a comparative study of CBMT approaches, using three types of systems: a statistical MT (SMT) system, an example-based MT (EBMT) system and a hybrid (EBMT-SMT) system. For our experiments we considered German-Romanian as language-pair, in this direction of translation, and a domain-restricted corpus, manually created and aligned (RoGER). The translation results have been both automatically and manually evaluated. For both evaluation types, the SMT system is ranked best in our experiments.

Typically, the lexicon models used in statistical machine translation systems do not include any kind of linguistic or contextual information, which often leads to problems in performing a correct word sense disambiguation. One way to deal with this problem within the statistical framework is to use maximum entropy methods. In this paper, we present how to use this type of information within a statistical machine translation system. We show that it is possible to significantly decrease training and test corpus perplexity of the translation models. In addition, we perform a rescoring of N-Best lists using our maximum entropy model and thereby yield an improvement in translation quality. Experimental results are presented on the so-called Verbmobil Task.

We revisit the one sense per discourse hypothesis of Gale et al. in the context of machine translation. Since a given sense can be lexicalized differently in translation, do we observe one translation per discourse? Analysis of manual translations reveals that the hypothesis still holds when using translations in parallel text as sense annotation, thus confirming that translational differences represent useful sense distinctions. Analysis of Statistical Machine Translation (SMT) output showed that despite ignoring document structure, the one translation per discourse hypothesis is strongly supported in part because of the low variability in SMT lexical choice. More interestingly, cases where the hypothesis does not hold can reveal lexical choice errors. A preliminary study showed that enforcing the one translation per discourse constraint in SMT can potentially improve translation quality, and that SMT systems might benefit from translating sentences within their entire document context.

Corpus-based machine translation (MT) has been the main approach to developing and implementing MT systems in both academia and the industry over the last three decades. In this field, the type and size of the corpus used for training MT engines have presented problems for both statistical MT (SMT) systems as well as neural MT (NMT) systems, being the two dominant corpusbased approaches. Moreover, language pairs such as Turkish-English have been understudied within this framework. This article aims to evaluate the translation quality in Turkish-to-English custom MT systems that have been trained on different corpus sizes and types. Two NMT engines and two SMT engines were trained on the KantanMT platform using two different training corpus types with either only domain-specific cardiology corpus or this corpus plus a mixed-domain corpus. The study conducted both automatic evaluations with metrics including BLEU, F-Measure and TER, as well as a comprehensive human evaluation with metrics including fluency, A/B test, and adequacy. Lastly, the study realized a separate, subjective terminology evaluation in order to investigate how differently MT systems handle terminology, as this is a crucial aspect for specific-domain text types such as cardiology. While the automatic evaluation results suggest the SMT engines to perform better than NMT engines, all human evaluators rated the mixed-domain NMT engine as the highest performing one. However, the terminology evaluation task demonstrated SMT to still be able to perform better and to commit less terminology errors, despite the industry and academia shifting toward NMT engines.

Assembling translations from multi-engine machine translation outputs

<div><p><em> Machine Translation has been an area of linguistic research for almost more than two decades now. But it still remains a very challenging task for devising an automated system which will deliver accurate translations of the natural languages. However, great strides have been made in this field with more success owing to the development of technologies of the web and off late there is a renewed interest in this area of research. </em></p><p><em> Technological advancements in the preceding two decades have influenced Machine Translation in a considerable way. Several MT approaches including Statistical Machine Translation greatly benefitted from these advancements, basically making use of the availability of extensive corpora. Web technology web3.0 uses the semantic web technology which represents any object or resource in the web both syntactically and semantically. This type of representation is very much useful for the computing systems to search any content on the internet similar to lexical search and improve the internet based translations making it more effective and efficient.</em></p><p><em> In this paper we propose a technique to improve existing statistical Machine Translation methods by making use of semantic web technology. Our focus will be on Tamil and Tamil to English MT. The proposed method could successfully integrate a semantic web technique in the process of WSD which forms part of the MT system. The integration is accomplished by using the capabilities of RDFS and OWL into the WSD component of the MT model. The contribution of this work lies in showing that integrating a Semantic web technique in the WSD system significantly improves the performance of a statistical MT system for a translation from Tamil to English.</em></p></div><em> In this paper we assume the availability of large corpora in Tamil language and specific domain based ontologies with Tamil semantic web technology using web3.0. We are positive on the expansion and development of Tamil semantic web and subsequently infer that Tamil to English MT will greatly improve the disambiguation concept apart from other related benefits. This method could enable the enhancement of translation quality by improving on word sense disambiguation process while text is translated from Tamil to English language. This method can also be extended to other languages such as Hindi and Indian Languages.</em>