Showing papers on "Computer-assisted translation published in 1994"

Language Engineering and Translation: Consequences of automation

Abstract: At a time when information technology has become a regular tool of specialised translators in all aspects of their work, it is useful to place the activity of technical translation into its appropriate environment and to describe it from the point of view of its role in the broader context of communication in which it occurs. The advent of automated alternatives to human translation has fundamentally affected the profession, its products and the relationship between translators and their clients.This book presents and discusses the process of translation against this background. The context in which translation is normally studied is widened in order to re-examine the process of translation as part of interlingual text production and to analyse the manner in which the new tools affect the product of translation.This book is of particular relevance in modern translator training courses. Contents 1. The language industry and translation, 2. Aspects of language, 3. Elements of communication theory, 4. A theory of text types and messages, 5. The nature of translation, 6. Specifications: Factors influencing the translation, 7. Preparation for translation, 8. Steps in translation, 9. Human and Machine Translation, 10 Pragmatic circumstances of automation, 11. Translation in an information technology environment. Bibliography + Index.

Machine translation apparatus for translating document with tag

Abstract: A machine translation apparatus, for translating a document including at least one tag, has a definition file, a supplementary translation information adding unit, and a machine translation engine. The definition file converts the tag into supplementary translation information for a machine translation operation. The supplementary translation information adding unit adds the supplementary translation information to the document in accordance with the definition file. The machine translation engine carries out the machine translation operation by accepting the document having the supplementary translation information. Therefore, a precise translation can be carried out without using human knowledge or the common sense of an operator.

A bidirectional, Transfer-Driven Machine Translation system for spoken dialogues

Abstract: This paper presents a brief overview of the bidirectional (Japanese and English) Transfer-Driven Machine Translation system, currently being developed at ATR. The aim of this development is to achieve bidirectional spoken dialogue translation using a new translation technique, TDMT, in which an example-based framework is fully utilized to translate the whole sentence. Although the translation coverage is presently restricted to conference registration, the system meets requirements for spoken dialogue translation, such as two-way translation, high speed, and high accuracy with robust processing.

Method and system for translating documents using translation handles

Abstract: A translation assistance program of a word processing program used to translate a source language document written in a source language to a target language document written in a target language. The translation assistance program displays the source language document on a translation screen portion of a display device. The translation assistance program then compares each source term in a product glossary with the source terms in the source language document. The product glossary associates each source term it stores with a target term which translates the source term into the target language. For each source term from the source language document which is stored in the product glossary, the translation assistance program: 1) underlines the source term in the source language document, 2) inserts a translation handle on the translation screen portion immediately after the source term, and 3) associates the translation handle with the target term which translates the source term into the target language. When the user decides to insert the target term at a current insertion point on the translation screen, the user invokes an insert target term command which contains the translation handle associated with the appropriate source term. In response, the translation assistance program retrieves the target term associated with the translation handle and inserts the target term at the current insertion point on the translation screen portion.

Coping with ambiguity in a large-scale machine translation system

Abstract: In an interlingual knowledge-based machine translation system, ambignuity arises when the source language analyzer produces more than one interlingua expression for a source sentence. This can have a negative impact on translation quality, since a target sentence may be produced from an unintended meaning. In this paper we describe the methods used in the KANT machine translation system to reduce or eliminate ambiguity in a large-scale application domain. We also test these methods on a large corpus of test sentences, in order to illustrate how the different disambiguation methods reduce the average number of parses per sentence.

Exploiting Structural Similarities in Machine Translation

Abstract: The central properties of an experimental system for machine translation, PONS, and the ideas behind them, are presented and motivated. PONS achieves a compromise between linguistic sophistication and efficiency by automatically exploiting structural similarities between source and target language in order to take “shortcuts” during the translation process. The system uses a PATR-type linguistic formalism to encode LFG-type grammatical descriptions and Situation Semantics-type semantic descriptions, and it is implemented in Medley Interlisp.

Large-scale machine translation: an interlingua approach

Abstract: In this paper we discuss the design and development of an interlingua for a large-scale MT project. We also discuss how the resulting KANT interlingua constrains complexity, supports staged development, evolves in a balanced fashion, and seeks maximal coverage. We address issues such as granularity of the data representation, its specification, the types of information it encodes, and how it supports a modular system architecture. Our experience shows that through a careful, reasoned design and implementation effort, it is possible to achieve multilingual target-language generation for extensive technical domains.

The automatic component of the LINGSTAT machine-aided translation system

Abstract: LINGSTAT is an interactive machine-aided translation system designed to increase the productivity of a translator. It is aimed both at experienced users whose goal is high quality translation, and inexperienced users with little knowledge of the source whose goal is simply to extract information from foreign language text. The system makes use of statistical information gathered from parallel and single-language corpora, but also draws from linguistic sources of knowledge. The first problem to be studied is Japanese to English translation, and work is progressing on a Spanish to English system.

Two methods for learning ALT-J/E translation rules from examples and a semantic hierarchy

Abstract: This paper presents our work towards the automatic acquisition of translation rules from Japanese-English translation examples for NTT's ALT-J/E machine translation system. We apply two machine learning algorithms: Haussler's algorithm for learning internal disjunctive concept and Quinlan's ID3 algorithm. Experimental results show that our approach yields rules that are highly accurate compared to the manually created rules.

Machine translation: history and general principles

Abstract: The translation of natural languages by machine, first dreamt of in the seventeenth century, has become a reality in the late twentieth. Computer programs are producing translations - not perfect translations, for that is an ideal to which no human translator can aspire; nor translations of literary texts, for the subtleties and nuances of poetry are beyond computational analysis; but translations of technical manuals, scientific documents, commercial prospectuses, administrative memoranda, medical reports. Machine translation is not primarily an area of abstract intellectual inquiry but the application of computer and language sciences to the development of systems answering practical needs. After an outline of basic features and general methods, the history of machine translation is traced from the pioneers and early systems of the 1950s and 1960s, the impact of the ALPAC report in the mid-1960s, the revival in the 1970s, commercial and operational systems of the 1980s, and research during the 1980s. 1. Basic features and terminology The term machine translation (MT) refers to computerized systems responsible for the production of translations with or without human assistance. It excludes computer-based translation tools which support translators by providing access to on-line dictionaries, remote terminology databanks, transmission and reception of texts, etc. The boundaries between machine-aided human translation (MAHT) and human-aided machine translation (HAMT) are often uncertain and the term computer-aided translation (CAT) can cover both, but the central core of MT itself is the automation of the full translation process. Although the ideal goal of MT systems may be to produce high-quality translation, in practice the output is revised ('post-edited'). It should be noted that in this respect MT does not differ from the output of most human translators which is normally revised by a second translator before dissemination. However, the types of errors produced by MT systems do differ from those of human translators (incorrect prepositions, articles, pronouns, verb tenses, etc.). Postediting is the norm, but in certain circumstances MT output may be unedited or only lightly revised, e.g. if it is intended only for specialists familiar with the text subject. Output might also serve as a rough draft for a human translator, i.e. as a 'pre-translation'. The translation quality of MT systems may be improved either, most obviously, by developing more sophisticated methods or by imposing certain restrictions on the input. The system may be designed, for example, to deal with texts limited to the 'sublanguage' (vocabulary and grammar) of a particular subject field (e.g. biochemistry) and/or document type (e.g. patents). Alternatively, input texts may be written in a 'controlled language', which restricts the range of vocabulary, avoids homonymy and polysemy and complex sentence structures. A third option is to require input texts to be marked ('pre-edited') with indicators of prefixes, suffixes, word divisions, phrase and clause boundaries, or of different grammatical categories (e.g. the noun co'nvict and its homonymous verb convi'ct). Finally, the system itself may refer problems of ambiguity and selection to human operators (usually translators) for resolution during the

Korean to English Translation Using Synchronous TAGs

Abstract: It is often argued that accurate machine translation requires reference to contextual knowledge for the correct treatment of linguistic phenomena such as dropped arguments and accurate lexical selection. One of the historical arguments in favor of the interlingua approach has been that, since it revolves around a deep semantic representation, it is better able to handle the types of linguistic phenomena that are seen as requiring a knowledge-based approach. In this paper we present an alternative approach, exemplified by a prototype system for machine translation of English and Korean which is implemented in Synchronous TAGs. This approach is essentially transfer based, and uses semantic feature unification for accurate lexical selection of polysemous verbs. The same semantic features, when combined with a discourse model which stores previously mentioned entities, can also be used for the recovery of topicalized arguments. In this paper we concentrate on the translation of Korean to English.

Lexical functions and machine translation

Abstract: This paper discusses the lexicographical concept of lexical functions (Mel'~uk and Zolkovsky, 1984) and their potential exploitation in the development of a machine translation lexicon designed to handle collocations. We show how lexical functions can be thought to reflect cross-linguistic meaning concepts for collocational structures and their translational equivalents, and therefore suggest themselves as some kind of languageindependent semantic primitives from which translation strategies can be developed. ~

A Practical Evaluation of an Integrated Translation Tool during a Large Scale Localisation Project

Abstract: This paper reports on the assessment of computer assisted translation tools for a large localisation company and the practical evaluation of one such tool.

Real-Time Spoken Language Translation Using Associative Processors

Abstract: This paper proposes a model using associative processors (APs) for real-time spoken language translation. Spoken language translation requires (1) an accurate translation and (2) a realtime response. We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation and target word selection. This paper will concentrate on the second requirement. In TDMT, example-retrieval (ER), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time. Our study has concluded that we only need to implement the ER for expressions including a frequent word on APs. Experimental results show that the ER can be drastically speeded up. Moreover, a study on communications between APs demonstrates the scalability against vocabulary size by extrapolation. Thus, our model, TDMT on APs, meets the vital requirements of spoken language translation.

Computer-assisted translation

Abstract: In computer-assisted translation, the computer program supports the translator, who translates the text himself, making all the essential decisions involved, whereas in machine translation, the translator supports the machine, that is to say that the computer or program translates the text, which is then edited by the translator, or not edited at all. Difficulties with such unedited output are described at machine translation.

Improvement in customizability using translation templates

Abstract: This paper outlines customization of a machine translation system using translation templates, which enable users to represent the bilingual knowledge needed for complex translation. To evaluate their effectiveness, we analyzed a bilingual text to estimate the improvement in customizability. The result shows that about 60% of mistranslated sentences can be translated as model translations by combining the proposed framework with the conventional customizing functions.

Self-Organizing Machine Translation: Example-Driven Induction of Transfer Functions.

Abstract: With the advent of faster computers, the notion of doing machine translation from a huge stored database of translation examples is no longer unreasonable. This paper describes an attempt to merge the Example-Based Machine Translation (EBMT) approach with psycholinguistic principles. A new formalism for context- free grammars, called *marker-normal form*, is demonstrated and used to describe language data in a way compatible with psycholinguistic theories. By embedding this formalism in a standard multivariate optimization framework, a system can be built that infers correct transfer functions for a set of bilingual sentence pairs and then uses those functions to translate novel sentences. The validity of this line of reasoning has been tested in the development of a system called METLA-1. This system has been used to infer English->French and English->Urdu transfer functions from small corpora. The results of those experiments are examined, both in engineering terms as well as in more linguistic terms. In general, the results of these experiments were psycho- logically and linguistically well-grounded while still achieving a respectable level of success when compared against a similar prototype using Hidden Markov Models.

Human strategies in translation and interpreting : what MT can learn from translators

Abstract: Translation which we think of as a broader concept above written translation as well as interpreting is basically a complex decision pro cess The decisions are based on available information Translation problems arise when the translator does not have necessary informa tion available at the moment of the translation This is where trans lation strategies come into e ect which translators use consciously or subconsciously We think that both forms of translation use basically the same type of strategies which are however not easy to detect or to measure Furthermore we think that the model of translation as a decision process also applies to machine translation In our paper we try to prove this using the example of reduction as a translation strategy Reduction is used both in written transla tion and in interpreting but is more prominent in the latter In our work we focus upon dialogue interpreting a non simultaneous type used in face to face interactions We try to outline how reduction strategies could be modelled in a machine interpreting system such as VERBMOBIL using the concept of the target of translation This paper was presented at the International Conference MT Ten Years On in Cran eld

The lexical unit in the METAL® MT system

Abstract: This paper tackles some of the problems encountered while developing the French-English version of the Siemens-Nixdorf METAL® computer-assisted translation system. The first part deals with the general problem of delimiting lexical units and the second part describes a few concrete translation problems and the solutions that have been adopted in this experimental transfer-based system. The role and importance of the lexicons is stressed, focussing more specifically on the possibility the lexicographer is given to manipulate complex structures and to control the translation process directly.

Interpreting compounds for machine translation

Abstract: The paper presents a procedure for interpretation of English compounds and lkn" automatic translation of such compounds into Slavic languages and French. In tile target languages, a compound nominal is as a role to be rendered by an NP with an adjective or genitive attribute, or with an attrilmtive participle construction. The model is based on Bierwisch's theory of word formation, which in turn is inspired by categorial grammar. The procedure is applied to a specific domain (asthma research).

The role of semantics in spoken dialogue translation systems

Abstract: In this paper, we consider the role of semantics in the spoken dialogue translation systems. We begin by looking at some of the key properties of an existing spoken dialogue system, namely the sundial system which provides flight and train information over the telephone, and how these properties affect the design methodology and functionality of spoken translation systems. These properties include the effects of speech processing, designing the system to meet the needs of users, and an analysis model which clearly separates the linguistic, conceptual, pragmatic and task levels. In this model many task functionalities are dependent upon, and sometimes realizable by, the semantic and pragmatic analysis components. Central to this approach, is the use of underspecified semantic representations which are further specified as and when required by domain and/or task analysis. This model can be applied in the development of spoken translation systems with two important effects: monolingual semantic and pragmatic analysis can be carried out by processes independent of, but correlated with, the (translation) function of the system; and the main functions of the transfer processes is to further specifying the representations for the target language and to deal with mismatches between source and target language representations. We illustrate this approach with semantic analyses of German utterances required for translation in the verbmobil spoken dialogue translation system.

DILEMMA: a tool for rapid manual translation

Abstract: Dilemma is a tool built to aid human translators in achieving higher productivity and better quality, by presenting lexical information which is automatically extracted from previous translations. The design decisions have been based on analyses of the human translation process. We present the ideas behind the tool, and outline the functionality. The system described has been used by professional translators with good results.

Automatic Aquisition of Semantic Attributes for User Defined Words m Japanese to English Machine Translation

Abstract: This paper proposes a method that automatically acquires the SAs (semantic attributes) of user defined words. Applying this method to the compilation of a user dictionary targeting newspaper article sentences and sentences of software design documents has revealed that the automatically determined SAs include 50 to 80% of the correct attributes. Translation experiments confirmed that the automatically acquired SAs improved translation quality by 6-13%.