Search results

The recent report for the Commission of the European Communities on current multilingual activities in the field of scientific and technical information and the 1977 conference on the same theme both included substantial sections on operational and experimental machine translation systems, and in its Plan of action the Commission announced its intention to introduce an operational machine translation system into its departments and to support research projects on machine translation. This revival of interest in machine translation may well have surprised many who have tended in recent years to dismiss it as one of the ‘great failures’ of scientific research. What has changed? What grounds are there now for optimism about machine translation? Or is it still a ‘utopian dream’ ? The aim of this review is to give a general picture of present activities which may help readers to reach their own conclusions. After a sketch of the historical background and general aims (section I), it describes operational and experimental machine translation systems of recent years (section II), it continues with descriptions of interactive (man‐machine) systems and machine‐assisted translation (section III), (and it concludes with a general survey of present problems and future possibilities section IV).

This paper seeks to examine the further integration of machine translation technologies with cross language information access in providing web users the capabilities of accessing information beyond language barriers. Machine translation and cross language information access are related technologies, and yet they have their own unique contributions in handling information in multiple languages. This paper aims to demonstrate that there are many opportunities to further integrate machine translation with cross language information access, and the combination can greatly empower web users in their information access.

Using English and Chinese as the language pair for studying, this paper looks at machine translation in query translation‐based cross language information access at multiple important aspects, which include query translation, relevance feedback, interactive cross language information access, out‐of‐vocabulary term translation, and data fusion. The goal is to obtain more insights about the wide range usages of machine translation in cross language information access, and to help the community to identify promising future directions for both machine translation and cross language access.

Machine translation can be applied effectively in many places in the whole cross language information access process. Queries translated by a machine translation system are high quality and are more robust in handling potential untranslated terms. Translation enhancement, a relevance feedback method using machine translation generated returned documents, is not only a valid technique by itself, but also helps to generate more robust cross language information access performance when combined with other relevance feedback techniques. Machine translation is also found to play a significant role in resolving untranslated terms and in data fusion.

This set of comparative empirical studies on integrating machine translation and cross language information access was performed on a common evaluation framework, and examined integration at multiple points of the cross language access process. The experimental results demonstrate the value of further integrating machine translation in cross language information access, and identify interesting future directions for both machine translation and cross language information access research.

This paper examines the types of machine aid which are suitable for use in a large translating operation such as those met in the European Community institutions. After reviewing the way in which these machine aids are already being used in large organizations, and examining the areas in which they can be of benefit to the running of the whole organization, the speaker warns of possible difficulties in introducing them. If these difficulties can be overcome, many advantages can be gained in a large organization by introducing a fully‐integrated word‐processing system in which all texts are stored in electronic archives and can be transmitted electronically from one work station to another, and from one country to another. The principles on which such a system could be developed can also be of immediate practical interest to the small user.

According to the Indian Sign Language Research and Training Centre (ISLRTC), India has approximately 300 certified human interpreters to help people with hearing loss. This paper aims to address the issue of Indian Sign Language (ISL) sentence recognition and translation into semantically equivalent English text in a signer-independent mode.

This study presents an approach that translates ISL sentences into English text using the MobileNetV2 model and Neural Machine Translation (NMT). The authors have created an ISL corpus from the Brown corpus using ISL grammar rules to perform machine translation. The authors’ approach converts ISL videos of the newly created dataset into ISL gloss sequences using the MobileNetV2 model and the recognized ISL gloss sequence is then fed to a machine translation module that generates an English sentence for each ISL sentence.

As per the experimental results, pretrained MobileNetV2 model was proven the best-suited model for the recognition of ISL sentences and NMT provided better results than Statistical Machine Translation (SMT) to convert ISL text into English text. The automatic and human evaluation of the proposed approach yielded accuracies of 83.3 and 86.1%, respectively.

It can be seen that the neural machine translation systems produced translations with repetitions of other translated words, strange translations when the total number of words per sentence is increased and one or more unexpected terms that had no relation to the source text on occasion. The most common type of error is the mistranslation of places, numbers and dates. Although this has little effect on the overall structure of the translated sentence, it indicates that the embedding learned for these few words could be improved.

Sign language recognition and translation is a crucial step toward improving communication between the deaf and the rest of society. Because of the shortage of human interpreters, an alternative approach is desired to help people achieve smooth communication with the Deaf. To motivate research in this field, the authors generated an ISL corpus of 13,720 sentences and a video dataset of 47,880 ISL videos. As there is no public dataset available for ISl videos incorporating signs released by ISLRTC, the authors created a new video dataset and ISL corpus.

During the course of recent years I have conducted my own independent study of the current activity concerning machine translation and computer‐aided translation. My goal has been not only to collect information, but to make a recommendation as to what position my own company — Interverbum — should take vis‐a‐vis the developments in the field, i.e. is machine translation, or can it be, a useful tool within my company's operations?

The purpose of this study is to evaluate freely available machine translation (MT) services' performance in translating metadata records.

Randomly selected metadata records were translated from English into Chinese using Google, Bing, and SYSTRAN MT systems. These translations were then evaluated using a five point scale for both fluency and adequacy. Missing count (words not translated) and incorrect count (words incorrectly translated) were also recorded.

Concerning both fluency and adequacy, Google and Bing's translations of more than 70 percent of test data received scores equal to or greater than three, representative of “non‐native Chinese” and “much coverage,” respectively. SYSTRAN scored lowest in both measures. However, these differences were not statistically significant. A Pearson correlation analysis demonstrated a strong relationship (r=0.86) between fluency and adequacy. Missing count and incorrect count strongly correlated with fluency and adequacy.

Most existing digital collections can be accessed in English alone. Few digital collections in the USA support multilingual information access (MLIA) that enables users of differing languages to search, browse, recognize and use information in the collections. Human translation is one solution, but it is neither time nor cost effective for most libraries. This study serves as a first step to understand the performance of current MT systems and to design effective and efficient MLIA services for digital collections.

The purpose of this paper is to address the knowledge acquisition bottleneck problem in natural language processing by introducing a new rule‐based approach for the automatic acquisition of linguistic knowledge.

The author has developed a new machine translation methodology that only requires a bilingual lexicon and a parallel corpus of surface sentences aligned at the sentence level to learn new transfer rules.

A first prototype of a web‐based Japanese‐English translation system called Japanese‐English translation using corpus‐based acquisition of transfer (JETCAT) has been implemented in SWI‐Prolog, and a Greasemonkey user script to analyze Japanese web pages and translate sentences via Ajax. In addition, linguistic information is displayed at the character, word, and sentence level to provide a useful tool for web‐based language learning. An important feature is customization; the user can simply correct translation results leading to an incremental update of the knowledge base.

This paper focuses on the technical aspects and user interface issues of JETCAT. The author is planning to use JETCAT in a classroom setting to gather first experiences and will then evaluate a real‐world deployment; also work has started on extending JETCAT to include collaborative features.

The research has a high practical impact on academic language education. It also could have implications for the translation industry by superseding certain translation tasks and, on the other hand, adding value and quality to others.

The paper presents an extended version of the paper receiving the Emerald Web Information Systems Best Paper Award at iiWAS2010.

The paper aims to enhance Arabic machine translation (MT) by proposing novel approaches: (1) a dimensionality reduction technique for word embeddings tailored for Arabic text, optimizing efficiency while retaining semantic information; (2) a comprehensive comparison of meta-embedding techniques to improve translation quality; and (3) a method leveraging self-attention and Gated CNNs to capture token dependencies, including temporal and hierarchical features within sentences, and interactions between different embedding types. These approaches collectively aim to enhance translation quality by combining different embedding schemes and leveraging advanced modeling techniques.

Recent works on MT in general and Arabic MT in particular often pick one type of word embedding model. In this paper, we present a novel approach to enhance Arabic MT by addressing three key aspects. Firstly, we propose a new dimensionality reduction technique for word embeddings, specifically tailored for Arabic text. This technique optimizes the efficiency of embeddings while retaining their semantic information. Secondly, we conduct an extensive comparison of different meta-embedding techniques, exploring the combination of static and contextual embeddings. Through this analysis, we identify the most effective approach to improve translation quality. Lastly, we introduce a novel method that leverages self-attention and Gated convolutional neural networks (CNNs) to capture token dependencies, including temporal and hierarchical features within sentences, as well as interactions between different types of embeddings. Our experimental results demonstrate the effectiveness of our proposed approach in significantly enhancing Arabic MT performance. It outperforms baseline models with a BLEU score increase of 2 points and achieves superior results compared to state-of-the-art approaches, with an average improvement of 4.6 points across all evaluation metrics.

The proposed approaches significantly enhance Arabic MT performance. The dimensionality reduction technique improves the efficiency of word embeddings while preserving semantic information. Comprehensive comparison identifies effective meta-embedding techniques, with the contextualized dynamic meta-embeddings (CDME) model showcasing competitive results. Integration of Gated CNNs with the transformer model surpasses baseline performance, leveraging both architectures' strengths. Overall, these findings demonstrate substantial improvements in translation quality, with a BLEU score increase of 2 points and an average improvement of 4.6 points across all evaluation metrics, outperforming state-of-the-art approaches.

The paper’s originality lies in its departure from simply fine-tuning the transformer model for a specific task. Instead, it introduces modifications to the internal architecture of the transformer, integrating Gated CNNs to enhance translation performance. This departure from traditional fine-tuning approaches demonstrates a novel perspective on model enhancement, offering unique insights into improving translation quality without solely relying on pre-existing architectures. The originality in dimensionality reduction lies in the tailored approach for Arabic text. While dimensionality reduction techniques are not new, the paper introduces a specific method optimized for Arabic word embeddings. By employing independent component analysis (ICA) and a post-processing method, the paper effectively reduces the dimensionality of word embeddings while preserving semantic information which has not been investigated before especially for MT task.

‘The telling of this story’ wrote Gottfried Keller at the start of his Romeo und Julia auf dem Dorfe, ‘might seem to be merely pointless repetition.’ The writer of yet another paper on technical translations may feel himself in the same position. What can he say that has not already been said? Faced with this problem, I first thought to solve it by describing my own experiences in this field, since one of my functions as an information officer is to operate a translation service. I am therefore inviting you to follow the progress of a typical translation through our system at BP Research Centre from the initial request to the final evaluation. However, to prevent this talk from being too parochial, I shall try to relate each stage of the process to the wider issues involved.

This paper proposes a number of essential requirements intended to provide direction for translation work‐benches of the future. The points made arise from a consideration of the problems and frustrations encountered during several years' experience in the use of proprietary and in‐house translation tools. The paper will also suggest innovations which may considerably improve the productivity and flexibility of future translation workbenches.