Incorporating prior knowledge like lexical constraints into the model's output to generate meaningful and coherent sentences has many applications in dialogue system, machine translation, image captioning, etc. However, existing RNN-based models incrementally generate sentences from left to right via beam search, which makes it difficult to directly introduce lexical constraints into the generated sentences. In this paper, we propose a new algorithmic framework, dubbed BFGAN, to address this challenge. Specifically, we employ a backward generator and a forward generator to generate lexically constrained sentences together, and use a discriminator to guide the joint training of two generators by assigning them reward signals. Due to the difficulty of BFGAN training, we propose several training techniques to make the training process more stable and efficient. Our extensive experiments on two large-scale datasets with human evaluation demonstrate that BFGAN has significant improvements over previous methods.
Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems. Notably, in low-resource settings, it proved to work effectively and efficiently, thanks to shared representation space that is forced across languages and induces a sort of transfer-learning. Furthermore, multilingual NMT enables so-called zero-shot inference across language pairs never seen at training time. Despite the increasing interest in this framework, an in-depth analysis of what a multilingual NMT model is capable of and what it is not is still missing. Motivated by this, our work (i) provides a quantitative and comparative analysis of the translations produced by bilingual, multilingual and zero-shot systems; (ii) investigates the translation quality of two of the currently dominant neural architectures in MT, which are the Recurrent and the Transformer ones; and (iii) quantitatively explores how the closeness between languages influences the zero-shot translation. Our analysis leverages multiple professional post-edits of automatic translations by several different systems and focuses both on automatic standard metrics (BLEU and TER) and on widely used error categories, which are lexical, morphology, and word order errors.
We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation. We propose a simple and effective way of utilizing such feedback in NMT training. We demonstrate how the common machine translation problem of domain mismatch between training and deployment can be reduced solely based on chunk-level user feedback. We conduct a series of simulation experiments to test the effectiveness of the proposed method. Our results show that chunk-level feedback outperforms sentence based feedback by up to 2.61% BLEU absolute.
Cross-lingual adaptation, a special case of domain adaptation, refers to the transfer of classification knowledge between two languages. In this article we describe an extension of Structural Correspondence Learning (SCL), a recently proposed algorithm for domain adaptation, for cross-lingual adaptation. The proposed method uses unlabeled documents from both languages, along with a word translation oracle, to induce cross-lingual feature correspondences. From these correspondences a cross-lingual representation is created that enables the transfer of classification knowledge from the source to the target language. The main advantages of this approach over other approaches are its resource efficiency and task specificity. We conduct experiments in the area of cross-language topic and sentiment classification involving English as source language and German, French, and Japanese as target languages. The results show a significant improvement of the proposed method over a machine translation baseline, reducing the relative error due to cross-lingual adaptation by an average of 30% (topic classification) and 59% (sentiment classification). We further report on empirical analyses that reveal insights into the use of unlabeled data, the sensitivity with respect to important hyperparameters, and the nature of the induced cross-lingual correspondences.
Machine Translation is the translation of one natural language into another using automated and computerized means. For a multilingual country like India, with the huge amount of information exchanged between various regions and in different languages in digitized format, it has become necessary to find an automated process from one language to another. In this paper, we take a look at the various Machine Translation System in India which is specifically built for the purpose of translation between the Indian languages. We discuss the various approaches taken for building the machine translation system and then discuss some of the Machine Translation Systems in India along with their features.
The IMPACT-es diachronic corpus of historical Spanish compiles over one hundred books --containing approximately 8 million words-- in addition to a complementary lexicon which links more than 10 thousand lemmas with attestations of the different variants found in the documents. This textual corpus and the accompanying lexicon have been released under an open license (Creative Commons by-nc-sa) in order to permit their intensive exploitation in linguistic research. Approximately 7% of the words in the corpus (a selection aimed at enhancing the coverage of the most frequent word forms) have been annotated with their lemma, part of speech, and modern equivalent. This paper describes the annotation criteria followed and the standards, based on the Text Encoding Initiative recommendations, used to the represent the texts in digital form. As an illustration of the possible synergies between diachronic textual resources and linguistic research, we describe the application of statistical machine translation techniques to infer probabilistic context-sensitive rules for the automatic modernisation of spelling. The automatic modernisation with this type of statistical methods leads to very low character error rates when the output is compared with the supervised modern version of the text.
Inferring evaluation scores based on human judgments is invaluable compared to using current evaluation metrics which are not suitable for real-time applications e.g. post-editing. However, these judgments are much more expensive to collect especially from expert translators, compared to evaluation based on indicators contrasting source and translation texts. This work introduces a novel approach for quality estimation by combining learnt confidence scores from a probabilistic inference model based on human judgments, with selective linguistic features-based scores, where the proposed inference model infers the credibility of given human ranks to solve the scarcity and inconsistency issues of human judgments. Experimental results, using challenging language-pairs, demonstrate improvement in correlation with human judgments over traditional evaluation metrics.
Machine Transliteration has come out to be an emerging and a very important research area in the field of machine translation. Transliteration basically aims to preserve the phonological structure of words. Proper transliteration of name entities plays a very significant role in improving the quality of machine translation. In this paper we are doing machine transliteration for English-Punjabi language pair using rule based approach. We have constructed some rules for syllabification. Syllabification is the process to extract or separate the syllable from the words. In this we are calculating the probabilities for name entities (Proper names and location). For those words which do not come under the category of name entities, separate probabilities are being calculated by using relative frequency through a statistical machine translation toolkit known as MOSES. Using these probabilities we are transliterating our input text from English to Punjabi.
Machine Translation for Indian languages is an emerging research area. Transliteration is one such module that we design while designing a translation system. Transliteration means mapping of source language text into the target language. Simple mapping decreases the efficiency of overall translation system. We propose the use of stemming and part-of-speech tagging for transliteration. The effectiveness of translation can be improved if we use part-of-speech tagging and stemming assisted transliteration.We have shown that much of the content in Gujarati gets transliterated while being processed for translation to Hindi language.
We live in a translingual society, in order to communicate with people from different parts of the world we need to have an expertise in their respective languages. Learning all these languages is not at all possible; therefore we need a mechanism which can do this task for us. Machine translators have emerged as a tool which can perform this task. In order to develop a machine translator we need to develop several different rules. The very first module that comes in machine translation pipeline is morphological analysis. Stemming and lemmatization comes under morphological analysis. In this paper we have created a lemmatizer which generates rules for removing the affixes along with the addition of rules for creating a proper root word.
For the past 60 years, Research in machine translation is going on. For the development in this field, a lot of new techniques are being developed each day. As a result, we have witnessed development of many automatic machine translators. A manager of machine translation development project needs to know the performance increase/decrease, after changes have been done in his system. Due to this reason, a need for evaluation of machine translation systems was felt. In this article, we shall present the evaluation of some machine translators. This evaluation will be done by a human evaluator and by some automatic evaluation metrics, which will be done at sentence, document and system level. In the end we shall also discuss the comparison between the evaluations.
Knowing the degree of semantic contrast between words has widespread application in natural language processing, including machine translation, information retrieval, and dialogue systems. Manually-created lexicons focus on opposites, such as {\rm hot} and {\rm cold}. Opposites are of many kinds such as antipodals, complementaries, and gradable. However, existing lexicons often do not classify opposites into the different kinds. They also do not explicitly list word pairs that are not opposites but yet have some degree of contrast in meaning, such as {\rm warm} and {\rm cold} or {\rm tropical} and {\rm freezing}. We propose an automatic method to identify contrasting word pairs that is based on the hypothesis that if a pair of words, $A$ and $B$, are contrasting, then there is a pair of opposites, $C$ and $D$, such that $A$ and $C$ are strongly related and $B$ and $D$ are strongly related. (For example, there exists the pair of opposites {\rm hot} and {\rm cold} such that {\rm tropical} is related to {\rm hot,} and {\rm freezing} is related to {\rm cold}.) We will call this the contrast hypothesis. We begin with a large crowdsourcing experiment to determine the amount of human agreement on the concept of oppositeness and its different kinds. In the process, we flesh out key features of different kinds of opposites. We then present an automatic and empirical measure of lexical contrast that relies on the contrast hypothesis, corpus statistics, and the structure of a {\it Roget}-like thesaurus. We show that the proposed measure of lexical contrast obtains high precision and large coverage, outperforming existing methods.
By investigating the distribution of phrase pairs in phrase translation tables, the work in this paper describes an approach to increase the number of n-gram alignments in phrase translation tables output by a sampling-based alignment method. This approach consists in enforcing the alignment of n-grams in distinct translation subtables so as to increase the number of n-grams. Standard normal distribution is used to allot alignment time among translation subtables, which results in adjustment of the distribution of n- grams. This leads to better evaluation results on statistical machine translation tasks than the original sampling-based alignment approach. Furthermore, the translation quality obtained by merging phrase translation tables computed from the sampling-based alignment method and from MGIZA++ is examined.
UNL system is designed and implemented by a nonprofit organization, UNDL Foundation at Geneva in 1999. UNL applications are application softwares that allow end users to accomplish natural language tasks, such as translating, summarizing, retrieving or extracting information, etc. Two major web based application softwares are Interactive ANalyzer (IAN), which is a natural language analysis system. It represents natural language sentences as semantic networks in the UNL format. Other application software is dEep-to-sUrface GENErator (EUGENE), which is an open-source interactive NLizer. It generates natural language sentences out of semantic networks represented in the UNL format. In this paper, NLization framework with EUGENE is focused, while using UNL system for accomplishing the task of machine translation. In whole NLization process, EUGENE takes a UNL input and delivers an output in natural language without any human intervention. It is language-independent and has to be parametrized to the natural language input through a dictionary and a grammar, provided as separate interpretable files. In this paper, it is explained that how UNL input is syntactically and semantically analyzed with the UNL-NL T-Grammar for NLization of UNL sentences involving verbs, pronouns and determiners for Punjabi natural language.
This paper considers the problem for estimating the quality of machine translation outputs which are independent of human intervention and are generally addressed using machine learning techniques.There are various measures through which a machine learns translations quality. Automatic Evaluation metrics produce good co-relation at corpus level but cannot produce the same results at the same segment or sentence level. In this paper 16 features are extracted from the input sentences and their translations and a quality score is obtained based on Bayesian inference produced from training data.
This paper describes a new, freely available, highly multilingual named entity resource for person and organisation names that has been compiled over seven years of large-scale multilingual news analysis combined with Wikipedia mining, resulting in 205,000 per-son and organisation names plus about the same number of spelling variants written in over 20 different scripts and in many more languages. This resource, produced as part of the Europe Media Monitor activity (EMM, http://emm.newsbrief.eu/overview.html), can be used for a number of purposes. These include improving name search in databases or on the internet, seeding machine learning systems to learn named entity recognition rules, improve machine translation results, and more. We describe here how this resource was created; we give statistics on its current size; we address the issue of morphological inflection; and we give details regarding its functionality. Updates to this resource will be made available daily.
The European Commission's (EC) Directorate General for Translation, together with the EC's Joint Research Centre, is making available a large translation memory (TM; i.e. sentences and their professionally produced translations) covering twenty-two official European Union (EU) languages and their 231 language pairs. Such a resource is typically used by translation professionals in combination with TM software to improve speed and consistency of their translations. However, this resource has also many uses for translation studies and for language technology applications, including Statistical Machine Translation (SMT), terminology extraction, Named Entity Recognition (NER), multilingual classification and clustering, and many more. In this reference paper for DGT-TM, we introduce this new resource, provide statistics regarding its size, and explain how it was produced and how to use it.
Dictionaries and phrase tables are the basis of modern statistical machine translation systems. This paper develops a method that can automate the process of generating and extending dictionaries and phrase tables. Our method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data. It uses distributed representation of words and learns a linear mapping between vector spaces of languages. Despite its simplicity, our method is surprisingly effective: we can achieve almost 90% precision@5 for translation of words between English and Spanish. This method makes little assumption about the languages, so it can be used to extend and refine dictionaries and translation tables for any language pairs.
Machine translation is research based area where evaluation is very important phenomenon for checking the quality of MT output. The work is based on the evaluation of English to Urdu Machine translation. In this research work we have evaluated the translation quality of Urdu language which has been translated by using different Machine Translation systems like Google, Babylon and Ijunoon. The evaluation process is done by using two approaches - Human evaluation and Automatic evaluation. We have worked for both the approaches where in human evaluation emphasis is given to scales and parameters while in automatic evaluation emphasis is given to some automatic metric such as BLEU, GTM, METEOR and ATEC.
This paper presents a novel approach to machine translation by combining the state of art name entity translation scheme. Improper translation of name entities lapse the quality of machine translated output. In this work, name entities are transliterated by using statistical rule based approach. This paper describes the translation and transliteration of name entities from English to Punjabi. We have experimented on four types of name entities which are: Proper names, Location names, Organization names and miscellaneous. Various rules for the purpose of syllabification have been constructed. Transliteration of name entities is accomplished with the help of Probability calculation. N-Gram probabilities for the extracted syllables have been calculated using statistical machine translation toolkit MOSES.