Sentence selection for improving the tuning process of a statistical machine translation system

Este artículo describe una estrategia de selección de frases para hacer el ajuste de un sistema de traducción estadístico basado en el decodificador Moses que traduce del español al inglés. En este trabajo proponemos dos posibilidades para realizar esta selección de las frases del corpus de validación que más se parecen a las frases que queremos traducir (frases de test en lengua origen). Con esta selección podemos obtener unos mejores pesos de los modelos para emplearlos después en el proceso de traducción y, por tanto, mejorar los resultados. Concretamente, con el método de selección basado en la medida de similitud propuesta en este artículo, mejoramos la medida BLEU del 27,17% con el corpus de validación completo al 27,27% seleccionando las frases para el ajuste. Estos resultados se acercan a los del experimento ORACLE: se utilizan las mismas frases de test para hacer el ajuste de los pesos. En este caso, el BLEU obtenido es de 27,51%.

Design, development and field evaluation of a Spanish into sign language translation system

This paper describes the design, development and field evaluation of a machine translation system from Spanish to Spanish Sign Language (LSE: Lengua de Signos Española). The developed system focuses on helping Deaf people when they want to renew their Driver’s License. The system is made up of a speech recognizer (for decoding the spoken utterance into a word sequence), a natural language translator (for converting a word sequence into a sequence of signs belonging to the sign language), and a 3D avatar animation module (for playing back the signs). For the natural language translator, three technological approaches have been implemented and evaluated: an example-based strategy, a rule-based translation method and a statistical translator. For the final version, the implemented language translator combines all the alternatives into a hierarchical structure. This paper includes a detailed description of the field evaluation. This evaluation was carried out in the Local Traffic Office in Toledo involving real government employees and Deaf people. The evaluation includes objective measurements from the system and subjective information from questionnaires. The paper details the main problems found and a discussion on how to solve them (some of them specific for LSE).

The use of deterministic parsers on sublanguage for machine translation

For more than forty years, research has been on going in the use of the computer in the processing of natural language. During this period methods have evolved, with various parsing techniques and grammars coming to prominence. Problems still exist, not least in the field of Machine Translation. However, one of the successes in this field is the translation of sublanguage. The present work reports Deterministic Parsing, a relatively new parsing technique, and its application to the sublanguage of an aircraft maintenance manual for Machine Translation. The aim has been to investigate the practicability of using Deterministic Parsers in the analysis stage of a Machine Translation system. Machine Translation, Sublanguage and parsing are described in general terms with a review of Deterministic parsing systems, pertinent to this research, being presented in detail. The interaction between machine Translation, Sublanguage and Parsing, including Deterministic parsing, is also highlighted. Two types of Deterministic Parser have been investigated, a Marcus-type parser, based on the basic design of the original Deterministic parser (Marcus, 1980) and an LR-type Deterministic Parser for natural language, based on the LR parsing algorithm. In total, four Deterministic Parsers have been built and are described in the thesis. Two of the Deterministic Parsers are prototypes from which the remaining two parsers to be used on sublanguage have been developed. This thesis reports the results of parsing by the prototypes, a Marcus-type parser and an LR-type parser which have a similar grammatical and linguistic range to the original Marcus parser. The Marcus-type parser uses a grammar of production rules, whereas the LR-type parser employs a Definite Clause Grammar(DGC).

Ebaluatoia: crowd evaluation of English-Basque machine translation

[EU]Lan honetan Ebaluatoia aurkezten da, eskala handiko ingelesa-euskara itzulpen automatikoko ebaluazio kanpaina, komunitate-elkarlanean oinarritua. Bost sistemaren itzulpen kalitatea konparatzea izan da kanpainaren helburua, zehazki, bi sistema estatistiko, erregeletan oinarritutako bat eta sistema hibrido bat (IXA taldean garatuak) eta Google Translate. Emaitzetan oinarrituta, sistemen sailkapen bat egin dugu, baita etorkizuneko ikerkuntza bideratuko duten zenbait analisi kualitatibo ere, hain zuzen, ebaluazio-bildumako azpi-multzoen analisia, iturburuko esaldien analisi estrukturala eta itzulpenen errore-analisia. Lanak analisi hauen hastapenak aurkezten ditu, etorkizunean zein motatako analisietan sakondu erakutsiko digutenak.

Cross-Lingual spoken language understanding from unaligned data using discriminative classification models and machine translation

This paper investigates several approaches to bootstrapping a new spoken language understanding (SLU) component in a target language given a large dataset of semantically-annotated utterances in some other source language. The aim is to reduce the cost associated with porting a spoken dialogue system from one language to another by minimising the amount of data required in the target language. Since word-level semantic annotations are costly, Semantic Tuple Classifiers (STCs) are used in conjunction with statistical machine translation models both of which are trained from unaligned data to further reduce development time. The paper presents experiments in which a French SLU component in the tourist information domain is bootstrapped from English data. Results show that training STCs on automatically translated data produced the best performance for predicting the utterance's dialogue act type, however individual slot/value pairs are best predicted by training STCs on the source language and using them to decode translated utterances. © 2010 ISCA.

Syntactic Based Machine Translation from English to Malayalam

Due to the emergence of multiple language support on the Internet, machine translation (MT) technologies are indispensable to the communication between speakers using different languages. Recent research works have started to explore tree-based machine translation systems with syntactical and morphological information. This work aims the development of Syntactic Based Machine Translation from English to Malayalam by adding different case information during translation. The system identifies general rules for various sentence patterns in English. These rules are generated using the Parts Of Speech (POS) tag information of the texts. Word Reordering based on the Syntax Tree is used to improve the translation quality of the system. The system used Bilingual English –Malayalam dictionary for translation.

UNITRAN: A Principle-Based Approach to Machine Translation

Machine translation has been a particularly difficult problem in the area of Natural Language Processing for over two decades. Early approaches to translation failed since interaction effects of complex phenomena in part made translation appear to be unmanageable. Later approaches to the problem have succeeded (although only bilingually), but are based on many language-specific rules of a context-free nature. This report presents an alternative approach to natural language translation that relies on principle-based descriptions of grammar rather than rule-oriented descriptions. The model that has been constructed is based on abstract principles as developed by Chomsky (1981) and several other researchers working within the "Government and Binding" (GB) framework. Thus, the grammar is viewed as a modular system of principles rather than a large set of ad hoc language-specific rules.

Machine Translation and the Disruption of Foreign Language Learning Activities

This study examines the question of how language teachers in a highly technologyfriendly university environment view machine translation and the implications that this has for the personal learning environments of students. It brings an activity-theory perspective to the question, examining the ways that the introduction of new tools can disrupt the relationship between different elements in an activity system. This perspective opens up for an investigation of the ways that new tools have the potential to fundamentally alter traditional learning activities. In questionnaires and group discussions, respondents showed general agreement that although use of machine translation by students could be considered cheating, students are bound to use it anyway, and suggested that teachers focus on the kinds of skills students would need when using machine translation and design assignments and exams to practice and assess these skills. The results of the empirical study are used to reflect upon questions of what the roles of teachers and students are in a context where many of the skills that a person needs to be able to interact in a foreign language increasingly can be outsourced to laptops and smartphones.

Machine translation and the disruption of foreign language learning activities

This study examines the question of how language teachers in a highly technology-friendly university environment view machine translation and the implications that this has for the personal learning environments of students. It brings an activity-theory perspective to the question, examining the ways that the introduction of new tools can disrupt the relationship between different elements in an activity system. This perspective opens up for an investigation of the ways that new tools have the potential to fundamentally alter traditional learning activities. In questionnaires and group discussions, respondents showed general agreement that although use of machine translation by students could be considered cheating, students are bound to use it anyway, and suggested that teachers focus on the kinds of skills students would need when using machine translation and design assignments and exams to practice and assess these skills. The results of the empirical study are used to reflect upon questions of what the roles of teachers and students are in a context where many of the skills that a person needs to be able to interact in a foreign language increasingly can be outsourced to laptops and smartphones.

Automatic Categorization for Improving Spanish into Spanish Sign Language Machine Translation

This paper describes a preprocessing module for improving the performance of a Spanish into Spanish Sign Language (Lengua de Signos Espanola: LSE) translation system when dealing with sparse training data. This preprocessing module replaces Spanish words with associated tags. The list with Spanish words (vocabulary) and associated tags used by this module is computed automatically considering those signs that show the highest probability of being the translation of every Spanish word. This automatic tag extraction has been compared to a manual strategy achieving almost the same improvement. In this analysis, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not assigned to any sign. The preprocessing module has been incorporated into two well-known statistical translation architectures: a phrase-based system and a Statistical Finite State Transducer (SFST). This system has been developed for a specific application domain: the renewal of Identity Documents and Driver's License. In order to evaluate the system a parallel corpus made up of 4080 Spanish sentences and their LSE translation has been used. The evaluation results revealed a significant performance improvement when including this preprocessing module. In the phrase-based system, the proposed module has given rise to an increase in BLEU (Bilingual Evaluation Understudy) from 73.8% to 81.0% and an increase in the human evaluation score from 0.64 to 0.83. In the case of SFST, BLEU increased from 70.6% to 78.4% and the human evaluation score from 0.65 to 0.82.