Translation Examples Research Articles

A ranking method for example based machine translation results by learning from user feedback

Example-Based Machine Translation (EBMT) is a corpus based approach to Machine Translation (MT), that utilizes the translation by analogy concept. In our EBMT system, translation templates are extracted automatically from bilingual aligned corpora by substituting the similarities and differences in pairs of translation examples with variables. In the earlier versions of the discussed system, the translation results were solely ranked using confidence factors of the translation templates. In this study, we introduce an improved ranking mechanism that dynamically learns from user feedback. When a user, such as a professional human translator, submits his evaluation of the generated translation results, the system learns “context-dependent co-occurrence rules” from this feedback. The newly learned rules are later consulted, while ranking the results of the subsequent translations. Through successive translation-evaluation cycles, we expect that the output of the ranking mechanism complies better with user expectations, listing the more preferred results in higher ranks. We also present the evaluation of our ranking method which uses the precision values at top results and the BLEU metric.

Maximum Entropy Model for Example-Based Machine Translation

Most example-based machine translation (EBMT) systems handle their translation examples using some heuristic measures based on human intuition. However, these heuristic rules are usually hard to be effectively organized to scale to incorporate diverse features to cover more language phenomenon and large domains. In this paper, we use machine learning approach for EBMT model design instead of human intuition. Maximum entropy (ME) model is introduced in order to adequately incorporate different kinds of features inherited in the translation examples effectively. At the same time, a multi-dimensional feature space is formally constructed to include various features of different aspects. In the experiments, the proposed model shows significant performance improvement.

Inducing translation templates with type constraints

This paper presents a generalization technique that induces translation templates from a given set of translation examples by replacing differing parts in the examples with typed variables. Since the type of each variable is inferred during the learning process, each induced template is also associated with a set of type constraints. The type constraints that are associated with a translation template restrict the usage of the translation template in certain contexts in order to avoid some of the wrong translations. The types of variables are induced using type lattices designed for both the source and target languages. The proposed generalization technique has been implemented as a part of an example-based machine translation system.

A system-theoretical view of EBMT

According to the system theory of von Bertalanffy (1968), Bertalanffy, a "system" is an entity that can be distinguished from its environment and that consists of several parts. System theory investigates the role of the parts, their interaction and the relation of the whole with its environment. System theory of the second order examines how an observer relates to the system. This paper traces some of the recent discussion of example-based machine translation (EBMT) and compares a number of EBMT and statistical MT systems. It is found that translation examples are linguistic systems themselves that consist of words, phrases and other constituents. Two properties of Luhmann's (2002) system theory are discussed in this context: EBMT has focussed on the properties of structures suited for translation and the design of their reentry points, and SMT develops connectivity operators which select the most likely continuations of structures. While technically the SMT and EBMT approaches complement each other, the principal distinguishing characteristic results from different sets of values which SMT and EBMT followers prefer.

Example-based machine translation based on tree–string correspondence and statistical generation

This paper describes an example-based machine translation (EBMT) method based on tree–string correspondence (TSC) and statistical generation. In this method, the translation example is represented as a TSC, which is a triple consisting of a parse tree in the source language, a string in the target language, and the correspondence between the leaf node of the source-language tree and the substring of the target-language string. For an input sentence to be translated, it is first parsed into a tree. Then the TSC forest which best matches the input tree is searched for. Finally the translation is generated using a statistical generation model to combine the target-language strings of the TSCs. The generation model consists of three features: the semantic similarity between the tree in the TSC and the input tree, the translation probability of translating the source word into the target word, and the language-model probability for the target-language string. Based on the above method, we build an English-to-Chinese MT system. Experimental results indicate that the performance of our system is comparable with phrase-based statistical MT systems.

Machine Translation Based on Translation Corresponding Tree Structure

A representation schema called translation corresponding tree (TCT) has been applied to a Portuguese to Chinese example-based machine translation system. The translation examples are annotated by the representation of the TCT structure. Each TCT describes not only the syntactic structure of the source sentence (i.e., Portuguese in our system) but also the translation correspondences (i.e., Chinese translation). In addition, the TCT nodes describe the corresponding linguistic relationships between the source and target languages. The translation examples can be effectively represented with this annotation schema and organized in the bilingual knowledge database or example base. In the real machine translation process, the target language is synthesized with higher quality by referring to the TCT translation information.

Example-based machine translation using efficient sentence retrieval based on edit-distance

An Example-Based Machine Translation (EBMT) system, whose translation example unit is a sentence, can produce an accurate and natural translation if translation examples similar enough to an input sentence are retrieved. Such a system, however, suffers from the problem of narrow coverage. To reduce the problem, a large-scale parallel corpus is required and, therefore, an efficient method is needed to retrieve translation examples from a large-scale corpus. The authors propose an efficient retrieval method for a sentence-wise EBMT using edit-distance. The proposed retrieval method efficiently retrieves the most similar sentences using the measure of edit-distance without omissions. The proposed method employs search-space division, word graphs, and an A* search algorithm. The performance of the EBMT was evaluated through Japanese-to-English translation experiments using a bilingual corpus comprising hundreds of thousands of sentences from a travel conversation domain. The EBMT system achieved a high-quality translation ability by using a large corpus and also achieved efficient processing by using the proposed retrieval method.

The untranslated grimms

This paper examines the issues surrounding the translation of the Grimms’ Kinder- und Hausmärchen, which were originally transcribed from oral tradition for an audience of children and adolescents but later gave rise to serious debate as to whether they should be classified as children's literature or should be more aimed at an adult target audience, since, according to various scholars, the Kinder- und Hausmärchen can be also viewed from several different perspectives such as Freudian, Jungian, Marxist and feminist. The paper mainly involves the exploration of different tales and concentrates on ‘untranslated’ fragments of texts, which were either omitted or altered in translations throughout the nineteenth and twentieth centuries. Therefore, a comparative translation approach is employed and different translations of the same tales are compared with the juxtaposition of source and target text examples. The German originals that are explored comparatively with the translated texts are the versions mainly used in translations throughout both the nineteenth and the twentieth centuries, and the translation examples are derived from various translations, such as Edgar Taylor's German Popular Stories (1823, 1826), Household Stories (1853), Margaret Hunt's Grimm's Household Tales (1884), Wanda Gág's Snow White and the Seven Dwarfs (1938) and Ralph Manheim's Grimm's Tales for Young and Old (1977).

Machine translation using recursive chain‐link‐type learning based on translation examples

AbstractRule‐based machine translation analyzes source‐language sentences using large‐scale linguistic knowledge that is given by the developer beforehand. However, it is difficult to give complete linguistic knowledge to the system ex ante because natural language has various linguistic phenomena. Therefore, we worked to develop learning‐based machine translation. In learning‐based machine translation, a system acquires translation rules automatically from translation examples that are pairs of source and target language sentences. However, existing learning‐based machine translation presents the problem that it requires a large number of similar translation examples. Consequently, it cannot acquire enough useful translation rules from sparse translation examples. This paper proposes a method of machine translation using Recursive Chain‐Link‐type Learning, which can acquire many useful translation rules from sparse translation examples. Our system, based on this method, efficiently acquires translation rules from each translation example without requiring two similar translation examples. Translation rules are acquired by extracting corresponding parts between source and target language sentences in translation examples. Our system determines those corresponding parts using previously acquired translation rules. Therefore, the system engenders a chain reaction in acquisition of new translation rules. Evaluation experiments using our system demonstrated an effective translation rate of 61.1%. Moreover, the effective translation rate was 85.0% when sufficient learning data were given to our system. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(2): 1–15, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10511

Jose de Torres's Treatise of 1736: General Rules for Accompanying on the Organ, Harpsichord, and the Harp, by Knowing Only How to Sing the Part, or a Bass in Canto Figurado (review)

Paul Murphy's edition and parallel English translation of the first thoroughbass treatise from Spain, José de Torres's four-part General Rules for Accompanying of 1736, is a welcome addition to the few Spanish music treatises available in English. What we know about early Spanish music theory comes largely from Francisco José León Tello's Estudios de historia de la teoría musical and La teoría española de la música en los siglos XVII y XVIII (Madrid: Consejo Superior de Investigaciones Cientificas, Instituto Español de Musicología, 1962 and 1974, respectively); unfortunately, neither has appeared in English translation. Torres (ca. 1665-1738), an organist and composer of some 171 known compositions, was also a publisher in Madrid of music and books on music, including the original edition of his thoroughbass treatise. In the present oblong-format volume, Murphy's transcription of the Spanish text--there is no facsimile edition of this treatise--and the music examples from the 1736 edition (in soprano and bass clefs) appear on the left page of each opening, with the parallel English translation and music examples in modern notation (in treble and bass clefs; occasionally, tenor clef) on the right. Much of the music is in unfigured bass (a feature distinguishing Torres's manual from most thoroughbass treatises from other countries), with figures appearing, when present, above the bass in the original edition and both above and below in the transcription.

Learning Translation Templates from Bilingual Translation Examples

A mechanism for learning lexical correspondences between two languages from sets of translated sentence pairs is presented. These lexical level correspondences are learned using analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond to the similar parts of the sentences in the target language. Similarly, the different parts must correspond to the respective parts in the translated sentences. The correspondences between similarities and between differences are learned in the form of translation templates. A translation template is a generalized translation exemplar pair where some components are generalized by replacing them with variables in both sentences and establishing bindings between these variables. The learned translation templates are obtained by replacing differences or similarities by variables. This approach has been implemented and tested on a set of sample training datasets and produced promising results for further investigation.

Learning translation templates from examples

This paper proposes a mechanism for learning lexical level correspondences between two languages from a set of translated sentence pairs. The proposed mechanism is based on an analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond to the similar parts of the sentences in the target language. Similarly, the different parts should correspond to the respective parts in the translated sentences. The correspondences between the similarities, and also differences are learned in the form of translation templates. The approach has been implemented and tested on a small training dataset and produced promising results for further investigation.

Example retrieval from a translation memory

Clustering of a translation memory is proposed to make the retrieval of similar translation examples from a translation memory more efficient, while a second contribution is a metric of text similarity which is based on both surface structure and content. Tests on the two proposed techniques are run on part of the CELEX database. The results reported indicate that the clustering of the translation memory results in a significant gain in the retrieval response time, while the deterioration in the retrieval accuracy can be considered to be negligible. The text similarity metric proposed is evaluated by a human expert and found to be compatible with the human perception of text similarity.

Implementing integrity constraints of EXPRESS in an active object-oriented database

A framework for engineering information exchange is proposed for an information-driven computer integrated manufacturing (CIM) system, using the ISO STEP EXPRESS specification language and an active object-oriented database. The framework allows both the engineering data and its integrity constraints specified using EXPRESS to be stored in the active object-oriented database. Using triggers for userdefined integrity constraints, the active object-oriented database enables application programs to share the engineering data without any concern about the integrity constraints. That is, integrity checking is performed by the database management system, not by individual application programs. Further, it can resolve the problem of engineering semantics loss, and integrate various existing computer aided engineering tools in a heterogeneous CIM environment. The translation framework is described along with appropriate translation examples. A prototype design system based on the framework and comparisons with ot...

MBT2: a method for combining fragments of examples in example-based translation

Example-Based Translation is a new approach to machine translation. The basic idea of this approach is very simple: it is to translate a sentence by using translation examples of similar sentences. One of the major issues of Example-Based Translation is to study the utilization of more than one translation example when translating one source sentence. This paper proposes MBT2, which is a method of translating complete sentences by using multiple examples. The representation, matching expression, is introduced, which represents the combination of fragments of translation examples. The translation process of MBT2 consists of three stages: 1. (1) Making a source-matching expression from a source sentence. 2. (2) Transferring a source-matching expression into a target-matching expression. 3. (3) Constructing a target sentence from a target-matching expression. This mechanism generates several translation candidates and the score of a translation is defined to select the best translation out of them.

Translation of clinical and neuropsychological instruments into French: the CERAD experience.

The increasing number of international and epidemiological studies of Alzheimer's disease points to the need for linguistically equivalent translations of measures for identifying the presence, types, and severity of dementia in cross-cultural populations. In translating the CERAD (Consortium to Establish a Registry for Alzheimer's Disease) neuropsychological instruments into French, several linguistic issues have emerged such as semantic, phonetic, and word-frequency equivalences. In verbal memory tests, these problems, though minor in appearance, can be major pitfalls in studies comparing cognitive function in populations differing in language. Description of the translation procedure and examples of problems encountered are presented, with measures taken to resolve them.

Poetic Translation Examples taken from Paul Valéry and Yunus Emre

Literary translation, especially poetic translation, is one of the rare domains where aesthetic, literary, and technical fields meet. This characteristic makes it the sort of work where a number of theoretical and practical problems converge. It is necessary to approach the issue on three essential planes. The first is theoretical: translation is an operation defined by rules; the second, functional: translation is a practical procedure, which is to say an a posteriori task; the third, specific: poetic translation is itself a poetic activity.Let us begin with the last. From the point of view of literary creation, there is actually no specific difference between the original text and that of the translation. For poet and translator alike take part in a creative act, each laboring according to his means and tastes. For each of them linguistic competence and poetic competence are essential. Indeed, the act of translating is based on a “task of purification of words and ideas” which requires the application of mental effort on the one hand to the problems and the constraints of the poetic art as such, and on the other hand, to the descriptive and analytic nature of language, which is also music. Which is to say that one should not see translation as a simple operation of a lexical order. Nor should one forget that each language requires a specific lexical classification.

Computer animated visual translation from natural language to sign language

AbstractComputer animation and visualization can facilitate communication between the hearing impaired and those with normal speaking capabilities. This paper presents a model of a system that is capable of translating text from a natural language into animated sign language. Techniques have been developed to analyse language and transform it into sign language in a systematic way. A hand motion coding method as applied to the hand motion representation, and control has also been investigated. Two translation examples are also given to demonstrate the practicality of the system.

Translating unrestricted relay ladder logic into Boolean form

Single-pass translation of unrestricted relay ladder logic (RLL) into an and/or Boolean form is described. A data representation of the ladder is specified for supporting computer-aided entry and flow displays, as well as the translation. The representation separates downward and upward vertical flow channels to simplify interpretation. The vertically separated representation can be derived during interactive keyboard entry of the model, without placing added demands on the user. The translation algorithm is explained in structured pseudocode and with a series of graphic translation examples. A dynamic data structure is given for the target and/or tree form. Algorithmic descriptions are done in the readable syntax of Modula-2, with pseudocode in place of specialized constructions.

Problems of machine translation systems: Effect of cultural differences on sentence structure

The potential and the limitation of current machine translation is discussed by comparing the output of human translation and that of virtual machine translation. Here, “virtual machine translation” means a kind of syntax-oriented literal translation which may be regarded as an idealized competence of today's practical machine translation. The above comparison shows that the main reason for the limitation or the incompleteness of current practical machine translation systems is the insufficient ability to treat “structural idiosyncrasies” of sentences. Also, some translation examples tell us that, without “understanding” the total meaning of the source sentence, it is quite difficult to manipulate the idiosyncrasies in sentence structure. Idiosyncratic gaps between source and target sentence structure usually originate in cultural differences, so that the computational treatment of these gaps is a very difficult problem. But the translation examples also give us some encouraging evidence that the principal technologies of today's not-yet-completed machine translation have sufficient potential for producing barely acceptable translation. The current practical efforts to treat such structural idiosyncrasies are also mentioned together with some long-range, basic-research type of approaches.