Rapid Prototyping of Domain-Specific Machine Translation Systems

Proceedings of the 18th conference on Computational linguistics -, 2000

The Computing Research Laboratory is currently developing technologies that allow rapid deployment of automatic translation capabilities. These technologies are designed to handle low-density languages for which resources, be that human informants or data in electronically readable form, are scarce. All tools are built in an incremental fashion, such that some simple tools (a bilingual dictionary or a glosser) can be delivered early in the development to support initial analysis tasks. More complex applications can be fielded in successive functional versions. The technology we demonstrate has first been applied to Persian-English machine translation within the Shiraz project and is currently extended to cover languages such as Arabic, Japanese, Korean and others.

2006

I, the undersigned, hereby declare that the work contained in this thesis is my own original work and that I have not previously, in its entirety or in part, submitted it at any university for a degree.

1995

In this paper we present the domain model used in the VERBMOBIL [10] project, a project concerned with face-to-face dialogue interpreting funded by the German Ministry of Research and Technology. The current version of the domain model, which is used in the VERBMOBIL demonstrator, has been implemented in the Description Logic (DL) system FLEX and contains approximately 300 concepts and 170 roles [16]. Instead of describing the details of this model we will rather motivate its main design criteria and illustrate its functionality by considering its use in the disambiguation process. In the next section we sketch the task of domain modeling in general, describe the particular requirements arising in the context of Machine Translation, and discuss the relationship between domain modeling and lexical semantics. In Section 3 we show how a contrastive analysis of source and target language forms the basis for a transfer-oriented conceptual hierarchy. Section 4 then illustrates how concept...

2015

In this paper, we study the impact of using a domain-specific bilingual lexicon on the performance of an Example-Based Machine Translation system. We conducted experiments for the EnglishFrench language pair on in-domain texts from Europarl (European Parliament Proceedings) and out-of-domain texts from Emea (European Medicines Agency Documents), and we compared the results of the Example-Based Machine Translation system against those of the Statistical Machine Translation system Moses. The obtained results revealed that adding a domain-specific bilingual lexicon (extracted from a parallel domain-specific corpus) to the general-purpose bilingual lexicon of the Example-Based Machine Translation system improves translation quality for both in-domain as well as outof-domain texts, and the Example-Based Machine Translation system outperforms Moses when texts to translate are related to the specific domain.

Comput. Informatics, 2016

The paper presents an attempt to automate all data creation processes of a rule-based shallow-transfer machine translation system. The presented methods were tested on four fully functional translation systems covering language pairs: Slovenian paired with Serbian, Czech, English and Estonian language. An extensive range of evaluation tests was performed to assess the applicability of the methods.

Most current Machine Translation (MT) systems do not improve with feedback from post-editors beyond the addition of corrected translations to parallel training data (for statistical and example-base MT) or to a memory database. Rule based systems to date improve only via manual debugging. In contrast, we propose a largely automated method for capturing more information from human post-editors, so that corrections may be performed automatically to translation grammar rules and lexical entries. This paper introduces a general framework for incorporating a refinement module into rule-based transfer MT systems. This framework allows for generalizing post-editing efforts in an effective way, by identifying and correcting rules semi-automatically on order to improve coverage and overall translation quality.

2000

We present a prototype of a transfer-based multilingual machine translation system from English and Spanish to Basque (a minority language). The system translates NPs and PPs in real texts solving interactively most of the ambiguities. One of our goals is to reuse and adapt wide-coverage tools and resources.

2007

It is generally acknowledged that the performance of rulebased machine translation (RMBT) systems can be greatly improved through domain-specific system adaptation. To that end, RBMT users often choose to invest significant resources into the development of ad hoc MT dictionaries. In this paper, we demonstrate that comparable customization effects can be achieved automatically. One effective way to do that is to post-edit the translations produced by a vanilla RBMT system using a specially-trained statistical machine translation (SMT) system. Our experiments indicate that this method is just as effective as manual customization of system dictionaries in reducing the need for manual postediting.

Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016

This paper presents the JU-USAAR English-German domain adaptive machine translation (MT) system submitted to the IT domain translation task organized in WMT-2016. Our system brings improvements over the in-domain baseline system by incorporating out-domain knowledge. We applied two methodologies to accelerate the performance of our in-domain MT system: (i) additional training material extraction from out-domain data using data selection method, and (ii) language model and translation model adaptation through interpolation. Our primary submission obtained a BLEU score of 34.5 (14.5 absolute and 72.5% relative improvements over baseline) and a TER score of 54.0 (14.7 absolute and 21.4% relative improvements over baseline).

By the time Machine Translation Summit X is held in September 2005, our group will have released an open-source machine translation toolbox as part of a large government-funded project involving four universities and three linguistic technology companies from Spain. The machine translation toolbox, which will most likely be released under a GPL-like license includes (a) the open-source engine itself, a modular shallowtransfer machine translation engine suitable for related languages and largely based upon that of systems we have already developed, such as interNOSTRUM for Spanish-Catalan and Traductor Universia for Spanish-Portuguese, (b) extensive documentation (including document type declarations) specifying the XML format of all linguistic (dictionaries, rules) and document format management files, (c) compilers converting these data into the highspeed (tens of thousands of words a second) format used by the engine, and (d) pilot linguistic data for Spanish-Catalan and Spanish-Galician and format management specifications for the HTML, RTF and plain text formats. After describing very briefly this toolbox, this paper aims at exploring possible consequences of the availability of this architecture, including the community-driven development of machine translation systems for languages lacking this kind of linguistic technology.