Metaphors of art in the English translations of Giorgio Vasari’s Le vite: a software-assisted enquiry

We propose a voice conversion framework to map the speech features of a source speaker to a target speaker based on deep neural networks (DNNs). Due to a limited availability of the parallel data needed for a pair of source and target speakers, speech synthesis and dynamic time warping are utilized to construct a large parallel corpus for DNN training. With a small corpus to train DNNs, a lower log spectral distortion can still be seen over the conventional Gaussian mixture model (GMM) approach, trained with the same data. With the synthesized parallel corpus, a speech naturalness preference score of about 54.5% vs. 32.8% and a speech similarity preference score of about 52.5% vs. 23.6% are observed for the DNN-converted speech from the large parallel corpus when compared with the DNN-converted speech from the small parallel corpus.

Based on a small, self-built Chinese-English parallel corpus, this study adopts a qualitative analysis approach to explore the features and English translation methods of ancient Chinese poetry and prose in The Governance of China IV. It is found that ancient Chinese poetry and prose are primarily cited directly from ancient articles. During the translation process, the translator skillfully applies a variety of methods, with a particular emphasis on free translation and its combination with literal translation. Furthermore, the translator flexibly incorporates amplification and omission as needed. This study provides valuable insights and practical methods for translating ancient Chinese poetry and prose in political documents with Chinese characteristics.

This paper presents a new model for word alignments between parallel sentences, which allows one to accurately estimate different parameters, in a computationally efficient way. An application of this model to bilingual terminology extraction, where terms are identified in one language and gussed, through the alignment process, in the other one, is also described. An experiment conducted on a small English-French parallel corpus gave results with high precision, demonstrating the validity of the model.

This article describes the methods involved in building a diachronic multilingual corpus devoted to Fine Arts, beginning with G. Vasari's Lives of the most excellent Italian architects, sculptors and painters (1568) as the fundamental source text in the field of Art History. Attention is given to automatic pre-alignment, the special proofreading protocol and segmentation rules developed to allow multilingual and/or diachronic alignment of multiple texts, and the difficulties inherent in annotating a multilingual database. A case study is offered, comparing the term “tondo” and its variants (e.g. “mezzo tondo”, “di tondo rilievo”) in Italian with their translations in English (De Vere 1912-15) and French (Leclanché 1839, Chastel 1981, Luciani 2002, Powell 2007). These later translations contain a greater variety of both lexicalized counterparts such as “medallion” or “lunette” as well as paraphrases, used to disambiguate and distinguish the various meanings of “tondo”, thus demonstrating how artistic vocabulary, which was still developing in 16th c. Italian, through its transmission to other languages, became more diversified and stable over time.

In this paper, we propose a new approach to improve the translation quality by adding the Key-Words of a sentence to the parallel corpus. The main idea of the approach is to find the key-words of sentences that cannot be properly translated by the model, and then put it or them in the training corpus in a separated line as a sentence. During our experiment, we use two statistical machine translation (SMT) systems, word-based SMT (ISI-rewrite) and phrase-based SMT (Moses), and a small parallel corpus (4,000 sentences) to check our assumption. To our glad, we get a better BLEU score than the original parallel text. It can improve about 6% in word-based SMT (isi-rewrite) and 4% in phrased-based SMT (Moses). At last we build a 120,000 English-Chinese parallel corpus in this way.

The validity of contrastive findings that base themselves on material from small parallel corpora may be questioned, and ever since the compilation of the English-Norwegian Parallel Corpus (ENPC) and English-Swedish Parallel Corpus (ESPC) some 20 years ago we have been aware of this. Recently, the ENPC has been expanded into the ENPC+, holding bidirectional translation data three times the size of the fiction part of the original ENPC. Drawing on material from the ENPC+, this paper replicates three contrastive studies made on the basis of the fiction part of the original ENPC to explore to what extent corpus size matters. The replica studies suggest that individual style, genre and date of publication are variables that may have a greater impact on the results than mere corpus size.

This study proposes a voice conversion-based approach to personalized text-to-speech (TTS) synthesis. The conversion functions, trained using a small parallel corpus with source and target speech data, can impose the voice characteristics of a target speaker on an existing synthesizer. Frame alignment between a pair of sentences in the parallel corpus is generally used for training voice conversion functions. However, with incorrect alignment, the resultant conversion functions may generate unacceptable conversion results. Traditional frame alignment using minimal spectral distance between the frame-based feature vectors of the source and the target phone sequences can be imprecise because the voice properties of the source and target phones inherently differ. In the proposed method, feature vectors of the parallel corpus are transformed into codewords in an eigenspace. A more precise frame alignment can be obtained by integrating the codeword occurrence distributions into distance estimation. In addition to the spectral property, a prosodic word/phrase boundary prediction model was constructed using an adaptive conditional random field (CRF) to generate personalized prosodic information. Objective and subjective tests were conducted to evaluate the performance of the proposed approach. The experimental results showed that the proposed voice conversion method, based on distribution-based alignment and prosodic word boundary detection, can improve the speech quality and speaker similarity of the converted speech. Compared to other methods, the evaluation results verified the improved performance of the proposed method.

As a typical low-resource language pair, besides severely limited by the scale of parallel corpus, Chinese-Lao language pair also has considerable linguistic differences, resulting in poor performance of Chinese-Lao neural machine translation (NMT) task. However, compared with the Chinese-Lao language pair, there are considerable cross-lingual similarities between Thai-Lao languages. According to these features, we propose a novel NMT approach. We first train Chinese-Thai and Thai-Lao NMT models wherein Thai is treated as pivot language. Then the transfer learning strategy is used to extract the encoder and decoder respectively from the two trained models. Finally, the encoder and decoder are combined into a new model and then fine-tuned based on a small-scale Chinese-Lao parallel corpus. We argue that the pivot language Thai can deliver more information to Lao decoder via linguistic similarity and help improve the translation quality of the proposed transfer-based approach. Experimental results demonstrate that our approach achieves 9.12 BLEU on Chinese-Lao translation task using a small parallel corpus, compared to the 7.37 BLEU of state-of-the-art Transformer baseline system using back-translation.

This paper presents a novel framework of voice conversion (VC) based on non-negative matrix factorization (NMF) using a small parallel corpus. In our previous work, a VC technique using NMF for noisy environments has been proposed, and it requires parallel exemplars (dictionary), which con sist of the source exemplars and target exemplars, having the same texts uttered by the source and target speakers. The large parallel corpus is used to construct a conversion function in NMF-based VC (in the same way as common GMM-based VC). In this paper, an adaptation matrix in an NMF frame work is introduced to adapt the source dictionary to the target dictionary. This adaptation matrix is estimated using a small parallel speech corpus only. The effectiveness of this method is confirmed by comparing its effectiveness with that of a con ventional NMF-based method and a GMM-based method in a noisy environment.

Cross-Lingual Information Retrieval (CLIR) provides flexibility to users to query in their regional (source) languages regardless the target documents languages. CLIR uses trending translation techniques Statistical Machine Translation (SMT) and Neural Machine Translation (NMT). SMT and NMT achieve good results for foreign languages but not for Indian languages due to non-absoluteness of the parallel corpus. Source language user queries may contain the Out Of Vocabulary (OOV) words which are not present in the parallel corpus such words may be skipped without performing translation by SMT. In this paper, a context-based translation algorithm is proposed to translate the OOV words by utilizing two unlabeled & unrelated large raw corpora (in source and target language) and a small bi-lingual parallel corpus. Since SMT performs better than NMT for Hindi to English translation as per the literature, therefore, experimental results are evaluated for FIRE datasets against baseline SMT. The proposed algorithm improves evaluation measures, Recall up to 6.04% (0.8785) for FIRE 2010 and up to 3.96% (0.7365) for FIRE 2011, & Mean Average Precision (MAP) up to 14.37% (0.3239) for FIRE 2010 and up to 5.46% (0.1988) for FIRE 2011, in comparison to the baseline SMT which achieves 0.8284 and 0.7084 Recall for FIRE 2010 and 2011, & 0.2832 and 0.1885 MAP for FIRE 2010 and 2011. An analysis for the number of OOV words shows that the proposed algorithm reduces the number of OOV more effectively, up to 0.81% for FIRE 2010 and 1.73% for FIRE 2011.

In order to construct a good machine translation system or make any natural language processing research for cross language information retrieval you must have a good parallel corpus. The Internet archive contains a lot of parallel documents. To construct a good parallel corpus from the Internet archive, you must have a good bilingual dictionary. This paper describes an algorithm to automatically extract an English/Arabic bilingual dictionary from parallel texts that exist in the Internet archive. The system should preferably be useful for many different language pairs. Unlike most of the systems done, our system can extract translation pairs from a very small parallel corpus. This new system can extract translations from only two sentences in one language and two sentences in the other language if the requirements of the system accomplished. Moreover, this system is able to extract word pairs that are translation of each other and the explanation of the Arabic or English word in the other language as well. The accuracy of the system is 59.1% in the case of one English word translated to one Arabic word, 23.9% in the case of one English word translated to more than one Arabic word (Arabic phrase), and 14.6% in the case of one Arabic word translated to more than one English word (English phrase).

The present article focuses on improving the performance of a hybrid Machine Translation (MT) system, namely PRESEMT. The PRESEMT methodology is readily portable to new language pairs, and allows the creation of MT systems with minimal reliance on expensive resources. PRESEMT is phrase-based and uses a small parallel corpus from which to extract structural transformations from the source language (SL) to the target language (TL). On the other hand, the TL language model is extracted from large monolingual corpora. This article examines the task of maximising the amount of information extracted from a very limited parallel corpus. Hence, emphasis is placed on the module that learns to segment into phrases arbitrary input text in SL, by extrapolating information from a limited-size parsed TL text, alleviating the need for an SL parser. An established method based on Conditional Random Fields (CRF) is compared here to a much simpler template-matching algorithm to determine the most suitable approach for extracting an accurate model. Experimental results indicate that for a limited-size training set, template-matching generates a superior model leading to higher quality translations.

Automatic text simplification is an active research area, and there are first systems for English, Spanish, Portuguese, and Italian. For German, no data-driven approach exists to this date, due to a lack of training data. In this paper, we present a parallel corpus of news items in German with corresponding simplifications on two complexity levels. The simplifications have been produced according to a well-documented set of guidelines. We then report on experiments in automatically simplifying the German news items using state-of-the-art neural machine translation techniques. We demonstrate that despite our small parallel corpus, our neural models were able to learn essential features of simplified language, such as lexical substitutions, deletion of less relevant words and phrases, and sentence shortening.

Recent text simplification approaches regard the task as a monolingual text-to-text generation inspired by machine translation. In particular, the transformer-based translation model outperform previous methods. Although machine translation approaches need a large-scale parallel corpus, parallel corpora for text simplification are very small compared to machine translation tasks. Therefore, we attempt a simple approach which fine-tunes the pre-trained language model for text simplification with a small parallel corpus. Specifically, we conduct experiments with the following two models: transformer-based encoder-decoder model and a language model that receives a joint input of original and simplified sentences, called TransformerLM. Thus, we show that TransformerLM, which is a simple text generation model, substantially outperforms a strong baseline. In addition, we show that fine-tuned TransformerLM with only 3,000 supervised examples can achieve performance comparable to a strong baseline trained by all supervised data.

This article explores how best to use lexical and statistical translation evidence together for cross‐language information retrieval (CLIR). Lexical translation evidence is assembled from Wikipedia and from a large machine‐readable dictionary, statistical translation evidence is drawn from parallel corpora, and evidence from co‐occurrence in the document language provides a basis for limiting the adverse effect of translation ambiguity. Coverage statistics for NII Testbeds and Community for Information Access Research (NTCIR) queries confirm that these resources have complementary strengths. Experiments with translation evidence from a small parallel corpus indicate that even rather rough estimates of translation probabilities can yield further improvements over a strong technique for translation weighting based on using Jensen–Shannon divergence as a term‐association measure. Finally, a novel approach to posttranslation query expansion using a random walk over the Wikipedia concept link graph is shown to yield further improvements over alternative techniques for posttranslation query expansion. Evaluation results on the NTCIR‐5 English–Korean test collection show statistically significant improvements over strong baselines.