Transfer-based Machine Translation Research Articles

A Machine Translation Like Approach to Generate Business Process Model from Textual Description

Modeling is one of the core tasks in Business Process Management (BPM). It represents the most critical step in the BPM life cycle and is considered as a time consuming and costly task. These challenges raised the question of how researchers can save this cost by building tools that could support modeling experts in their work to reduce the manual workload. In this paper, we propose a Machine Translation (MT) like approach to deal with the problem of generating a business process model based on a textual description. We chose to follow a semantic transfer-based MT approach. Our approach consists of two main phases: The natural Language Analysis phase and BPMN diagram generation. Natural Language Analysis phase aims to analyze the text and extract the required knowledge. One of the main outputs for this phase is a Concept Map which summarizes the concepts of the related domain and the relationships between these concepts. This map represents a background for our processing in the second phase where we try to generate the “translation”, which is the BPMN diagram in our case. We achieve our goal in the second phase via a set of semantic, syntactic, and morphological manipulations. The approach has been implemented and evaluated usinga similarity metric based on the Graph Edit Distance. The results show that the proposed approach was able to generate models that are more than 81% similar to those created manually by a human, outperforming the state of the art in this topic.

Productivity of Machine Translation

This article is about the field of technical translation which is called machine translation (MT), or machine-assisted translation. This method of translation uses various types of computer software to generate translations from a source language to a target language without the assistance of a human. There are different methods of machine translation. A plethora of machine translators in the form of free search engines are available online. However, within the field of technical communication, there are two basic types of machine translators, which are able to translate massive amounts of text at a time. There are transfer-based and data-driven machine translators. Transfer-based machine translation systems, which are quite costly to develop, are built by linguists who determine the grammar rules for the source and target languages. The machine works within the rules and guidelines developed by the linguist. Due to the nature of developing rules for the system, this can be very time-consuming and requires an extensive knowledge base about the structures of the languages on the part of the linguist; nonetheless, the majority of commercial machine translators are transfer-based machines. .

Phrase-Based Statistical Machine Translation of Hindi Poetries into English by incorporating Word Sense Disambiguation

Statistical machine translation (SMT) is a variant of machine translation where the translations are handled with statistically defined rules. Numerous researchers have attempted to build the framework which can comprehend the different dialects to translate from one source language to another target language. However, the focus on translation of poetry is less. Reliable and rapid transliteration of the poetry is very mandatory for the execution of the computer to translate the poem from one language to another. The existing approach has several issues, such as, time consumption, quality of the translation process, and matching of similar words. To overcome these issues, we propose a phrase-based statistical machine translation (PSMT) with special adherence to word sense disambiguation (WSD). The quality of the translation is increased by sensing the ambiguous words with WSD. The Hindi WordNet along with the Lesk algorithm identifies the ambiguous words and senses the exact meaning before the phrase extraction. Finally, the proposed method is compared with machine translation schemes, such as, rule-based machine translation and transfer-based machine translation. The experimental results suggest that the proposed method performed well with the inclusion of WSD in the PSMT technique.

Word Reordering for Translation into Korean Sign Language Using Syntactically-guided Classification

Machine translation aims to break the language barrier that prevents communication with others and increase access to information. Deaf people face huge language barriers in their daily lives, including access to digital and spoken information. There are very few digital resources for sign language processing. In this article, we present a transfer-based machine translation system for translating Korean-to-Korean Sign Language (KSL) glosses, mainly composed of (1) dictionary-based lexical transfer and (2) a hybrid syntactic transfer based on a data-driven model. In particular, we formulate complicated word reordering problems in syntactic transfer as multi-class classification tasks and propose “syntactically guided” data-driven syntactic transfer. The core part of our study is a neural classification model for reordering order-important constituent pairs with a reordering task that is newly designed for Korean-to-KSL translation. The experiment results evaluated on news transcript data show that the proposed system achieves a BLEU score of 0.512 and a RIBES score of 0.425, significantly improving upon the baseline system performance.

A Bicolano-to-Tagalog Transfer-Based Machine Translation System

The Bicolano-Tagalog Transfer-based Machine Translation System is a unidirectional machine translator for languages Bicolano and Tagalog. The transfer-based approach is divided into three phase: Pre-Processing Analysis, Morphological Transfer, and Sentence Generation. The system analyze first the source language (Bicolano) input to create some internal representation. This includes the tokenizer, stemmer, POS tag and parser. Through transfer rules, it then typically manipulates this internal representation to transfer parsed source language syntactic structure into target language syntactic structure. Finally, the system generates Tagalog sentence from own morphological and syntactic information. Each phase will undergo training and evaluation test for the competence of end-results. Overall performance shows a 71.71% accuracy rate.

Development of Telugu-Tamil Transfer-Based Machine Translation System: An Improvization Using Divergence Index

Abstract Building an automatic, high-quality, robust machine translation (MT) system is a fascinating yet an arduous task, as one of the major difficulties lies in cross-linguistic differences or divergences between languages at various levels. The existence of translation divergence precludes straightforward mapping in the MT system. An increase in the number of divergences also increases the complexity, especially in linguistically motivated transfer-based MT systems. This paper discusses the development of Telugu-Tamil transfer-based MT and how a divergence index (DI) is built to quantify the number of parametric variations between languages in order to improve the success rate of MT. The DI facilitates MT in proposing where to put efforts for the given language pair to attain better and faster results. In addition, handling strategies of different types of divergences in a transfer-based approach to MT are discussed. The paper also includes the evaluation method and how an improvization takes place with the application of DI in MT.

Implementing universal dependency, morphology, and multiword expression annotation standards for Turkish language processing

Released only a year ago as the outputs of a research project (``Parsing Web 2.0 Sentences'', supported in part by a TÜBİTAK 1001 grant (No. 112E276) and a part of the ICT COST Action PARSEME (IC1207)), IMST and IWT are currently the most comprehensive Turkish dependency treebanks in the literature. This article introduces the final states of our treebanks, as well as a newly integrated hierarchical categorization of the multiheaded dependencies and their organization in an exclusive deep dependency layer in the treebanks. It also presents the adaptation of recent studies on standardizing multiword expression and named entity annotation schemes for the Turkish language and integration of benchmark annotations into the dependency layers of our treebanks and the mapping of the treebanks to the latest Universal Dependencies (v2.0) standard, ensuring further compliance with rising universal annotation trends. In addition to significantly boosting the universal recognition of Turkish treebanks, our recent efforts have shown an improvement in their syntactic parsing performance (up to 77.8{\%}/82.8{\%} LAS and 84.0{\%}/87.9{\%} UAS for IMST/IWT, respectively). The final states of the treebanks are expected to be more suited to different natural language processing tasks, such as named entity recognition, multiword expression detection, transfer-based machine translation, semantic parsing, and semantic role labeling.

Words ordering and corresponding verb-subject agreements in English-Arabic machine translation: Hybrid-based approach

Recently Machine Translation (MT) has become a testing ground for many ideas in artificial intelligence (AI) as well as linguistics. Word ordering plays an important role in the translation process between languages. This research is attempting to examine the implications of using verb subject object (VSO) and subject verb object (SVO) words order on the agreement requirements in MT. Approach: The main objective of this research is to develop an English- Arabic Hybrid-Based Machine Translation (EA-HBMT) to improve the quality of MT from English to Arabic. Transfer-based MT is used to obtain an intermediate representation that captures the meaning of the original sentence in order to generate the correct translation. Example based-technique is used as well to handle the irregular cases. Semantic analysis process is mainly conducted to detect the statements that require the use of SVO construction rather than VSO. Results: we have constructed an agreement and ordering tests suite; that has been used in testing different agreement and ordering features in four Arabic MT systems, they are, ALKAFI, GOOGLE and TARJIM SAKHR versus EA-HBMT. These examples have been used in exploring and evaluating the agreement and ordering problems throughout three experiments. In the first experiment we have classified the problems that cause that agreement and ordering into twelve and we compare between the four systems outputs with the original translation of the input text based on these twelve problems. In the second experiment we tested each statement separately, by comparing the particular on-line translation with the original human translation based on the number of the correct translated words in the target language. Conclusion: Based on the achieved results, we have managed to perform the Symantec analysis within Arabic source texts by using hybrid-based machine translation and also achieved reasonable improvements in translation quality over related approaches.

Using information structure to improve transfer-based MT

This paper hypothesizes that transfer-based machine translation systems can be improved by encoding information structure in both the source and target grammars, and preserving information structure in the transfer stage. We explore how information structure can be represented within the HPSG/MRS formalism (Pollard and Sag, 1994; Copestake et al., 2005) and how it can help refine multilingual MT. Building upon that framework, we provide a sample translation between English and Japanese and check the feasibility of the proposals in small-scale translation systems built with the HPSG/MRS-based LOGON MT infrastructure (Oepen et al., 2007). Our experiment shows the information structure-based MT system that we propose in this paper reduces the number of translations 75.71% for Japanese and 80.23% for Korean. The dramatic reductions in the number of translations is expected to make a contribution to our HPSG/MRS-based MT in terms of latency as well as accuracy.

Machine Translation of Noun Phrases from Arabic to English Using Transfer-Based Approach

Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it shoul d fulfill the specific requirement of this language . Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve a s rules for the ordering of sentence constituents. These rules draw their information from the syntact ic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by usin g transfer-based approach. A system called Npae- Rbmt has been developed in this research. Transfer- based machine translation is one instance of rule- based machine-translation approaches and is current ly one of the most widely used methods of machine translation. The idea of transfer-based mac hine translation it is necessary to have an intermediate representation that captures the mean ing of the original sentence in order to generate the correct translation. Using advantages of transf er-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic an alysis goes deeper-as the representation of analysi s step becomes more abstract. In fact, a major goal o f MT research is to define a level of analysis whic h is so deep in which transfer-based machine translat ion is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6%. These results proved the viability of this a pproach for distant languages. Conclusion: Based on the achieved results, we have managed to perform th e syntactic reordering within an Arabic noun phrases to English translation task by using transf er-based machine translation and also achieved reasonable improvements in translation quality over related approach.

Sulis: An Open Source Transfer Decoder for Deep Syntactic Statistical Machine Translation

Sulis: An Open Source Transfer Decoder for Deep Syntactic Statistical Machine Translation In this paper, we describe an open source transfer decoder for Deep Syntactic Transfer-Based Statistical Machine Translation. Transfer decoding involves the application of transfer rules to a SL structure. The N-best TL structures are found via a beam search of TL hypothesis structures which are ranked via a log-linear combination of feature scores, such as translation model and dependency-based language model.

ScaleMT: a Free/Open-Source Framework for Building Scalable Machine Translation Web Services

Machine translation web services usage is growing amazingly mainly because of the translation quality and reliability of the service provided by the Google Ajax Language API. To allow the open-source machine translation projects to compete with Google’s one and gain visibility on the internet, we have developed ScaleMT: a free/open-source framework that exposes existing machine translation engines as public web services. This framework is highly scalable as it can run coordinately on many servers, efficiently managing the resources needed by the engines, and its API is compatible with Google’s one. ScaleMT is based on previous efforts to build a web service for the Apertium machine translation toolbox, but we have also tested it with Matxin, another free/open-source transfer-based machine translation engine. Additionally, we have compared ScaleMT to an alternative web service implementation for Apertium, obtaining satisfactory results.

A Minimal Recursion Semantic Analysis of Locatives

The article describes a pilot implementation of a grammar containing different types of locative PPs. In particular, we investigate the distinction between static and directional locatives, and between different types of directional locatives. Locatives may act as modifiers as well as referring expressions depending on the syntactic context. We handle this with a single lexical entry. The implementation is of Norwegian locatives, but English locatives are both discussed and compared to Norwegian locatives. The semantic analysis is based on a proposal by Markus Kracht (2002), and we show how this analysis can be incorporated into Minimal Recursion Semantics (MRS) (Copestake et al. 2005). We discuss how the resulting system may be applied in a transfer-based machine translation system, and how we can map from a shallow MRS representation to a deeper semantic representation.

Experiments with a Hindi-to-English transfer-based MT system under a miserly data scenario

We describe an experiment designed to evaluate the capabilities of our trainable transfer-based (Xfer) machine translation approach, as applied to the task of Hindi-to-English translation, and trained under an extremely limited data scenario. We compare the performance of the Xfer approach with two corpus-based approaches---Statistical MT (SMT) and Example-based MT (EBMT)---under the limited data scenario. The results indicate that the Xfer system significantly outperforms both EBMT and SMT in this scenario. Results also indicate that automatically learned transfer rules are effective in improving translation performance, compared with a baseline word-to-word translation version of the system. Xfer system performance with a limited number of manually written transfer rules is, however, still better than the current automatically inferred rules. Furthermore, a "multiengine" version of our system that combined the output of the Xfer and SMT systems and optimizes translation selection outperformed both individual systems.

MT for Minority Languages Using Elicitation-Based Learning of Syntactic Transfer Rules

The AVENUE project contains a run-time machine translation program that is surrounded by pre- and post-run-time modules. The post-run-time module selects among translation alternatives. The pre-run-time modules are concerned with elicitation of data and automatic learning of transfer rules in order to facilitate the development of machine translation between a language with extensive resources for natural language processing and a language with few resources for natural language processing. This paper describes the run-time transfer-based machine translation system as well as two of the pre-run-time modules: elicitation of data from the minority language and automated learning of transfer rules from the elicited data.

The theoretical basis of MiMo

The purpose of this paper is to describe and motivate the leading ideas behind the MiMo notation, a formalism for transfer-based machine translation which is especially appropriate for intermediate representations based on Dependency Grammar. The most important of these ideas concern properties of the translation relation such as compositionality, reversibility, modularity, and autonomy of levels of description. The final section considers some issues relating to rule interaction.