scholarly journals The Alignment Template Approach to Statistical Machine Translation

2004 ◽  
Vol 30 (4) ◽  
pp. 417-449 ◽  
Author(s):  
Franz Josef Och ◽  
Hermann Ney
Keyword(s):  
Machine Translation ◽  
Word Order ◽  
Search Algorithm ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Linear Modeling ◽  
Translation Model ◽  
Log Linear ◽  
Translation Systems ◽  
English Canadian

A phrase-based statistical machine translation approach — the alignment template approach — is described. This translation approach allows for general many-to-many relations between words. Thereby, the context of words is taken into account in the translation model, and local changes in word order from source to target language can be learned explicitly. The model is described using a log-linear modeling approach, which is a generalization of the often used source-channel approach. Thereby, the model is easier to extend than classical statistical machine translation systems. We describe in detail the process for learning phrasal translations, the feature functions used, and the search algorithm. The evaluation of this approach is performed on three different tasks. For the German-English speech Verbmobil task, we analyze the effect of various system components. On the French-English Canadian Hansards task, the alignment template system obtains significantly better results than a single-word-based translation model. In the Chinese-English 2002 National Institute of Standards and Technology (NIST) machine translation evaluation it yields statistically significantly better NIST scores than all competing research and commercial translation systems.

scholarly journals Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation

2003 ◽  
Vol 29 (1) ◽  
pp. 97-133 ◽  
Author(s):  
Christoph Tillmann ◽  
Hermann Ney
Keyword(s):  
Dynamic Programming ◽  
Machine Translation ◽  
Search Algorithm ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Search Procedure ◽  
Beam Search ◽  
Translation Model ◽  
Novel Technique ◽  
The Traveling Salesman Problem

In this article, we describe an efficient beam search algorithm for statistical machine translation based on dynamic programming (DP). The search algorithm uses the translation model presented in Brown et al. (1993). Starting from a DP-based solution to the traveling-salesman problem, we present a novel technique to restrict the possible word reorderings between source and target language in order to achieve an efficient search algorithm. Word reordering restrictions especially useful for the translation direction German to English are presented. The restrictions are generalized, and a set of four parameters to control the word reordering is introduced, which then can easily be adopted to new translation directions. The beam search procedure has been successfully tested on the Verbmobil task (German to English, 8,000-word vocabulary) and on the Canadian Hansards task (French to English, 100,000-word vocabulary). For the medium-sized Verbmobil task, a sentence can be translated in a few seconds, only a small number of search errors occur, and there is no performance degradation as measured by the word error criterion used in this article.

scholarly journals Training Human Translators as Opposed to Programming Machine Translation Systems: A Performative Model

2009 ◽  
Vol 50 (4) ◽  
Author(s):  
Arvi Tavast
Keyword(s):  
Machine Translation ◽  
Evaluation System ◽  
Target Language ◽  
Communicative Intent ◽  
Translation Model ◽  
Proposed Model ◽  
Translation Systems

Abstract This paper combines the communicative model of translation with performative linguistics to arrive at a translation model that is meant to proactively shape the attitudes of future translators. Central to this model is the claim that the translator, like any communicator, has a communicative intent that gets expressed in the target text. This is contrasted with machine translation, which is concerned with finding equivalents to translation units without actually having anything to say in the target language. The paper concludes by indicating a way of building a translation evaluation system on the proposed model.

Improving Statistical Machine Translation by Adapting Translation Models to Translationese

2013 ◽  
Vol 39 (4) ◽  
pp. 999-1023 ◽  
Author(s):  
Gennadi Lembersky ◽  
Noam Ordan ◽  
Shuly Wintner
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Common Assumption ◽  
Parallel Corpora ◽  
The Common ◽  
The Right ◽  
Translation Systems ◽  
Parallel Texts

Translation models used for statistical machine translation are compiled from parallel corpora that are manually translated. The common assumption is that parallel texts are symmetrical: The direction of translation is deemed irrelevant and is consequently ignored. Much research in Translation Studies indicates that the direction of translation matters, however, as translated language (translationese) has many unique properties. It has already been shown that phrase tables constructed from parallel corpora translated in the same direction as the translation task outperform those constructed from corpora translated in the opposite direction. We reconfirm that this is indeed the case, but emphasize the importance of also using texts translated in the “wrong” direction. We take advantage of information pertaining to the direction of translation in constructing phrase tables by adapting the translation model to the special properties of translationese. We explore two adaptation techniques: First, we create a mixture model by interpolating phrase tables trained on texts translated in the “right” and the “wrong” directions. The weights for the interpolation are determined by minimizing perplexity. Second, we define entropy-based measures that estimate the correspondence of target-language phrases to translationese, thereby eliminating the need to annotate the parallel corpus with information pertaining to the direction of translation. We show that incorporating these measures as features in the phrase tables of statistical machine translation systems results in consistent, statistically significant improvement in the quality of the translation.

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

2010 ◽  
Vol 93 (1) ◽  
pp. 17-26 ◽  
Author(s):  
Yvette Graham
Keyword(s):  
Open Source ◽  
Linear Combination ◽  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Beam Search ◽  
Translation Model ◽  
Transfer Rules ◽  
Log Linear

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.

scholarly journals N-gram-based Machine Translation

2006 ◽  
Vol 32 (4) ◽  
pp. 527-549 ◽  
Author(s):  
José B. Mariño ◽  
Rafael E. Banchs ◽  
Josep M. Crego ◽  
Adrià de Gispert ◽  
Patrik Lambert ◽  
...  
Keyword(s):  
Linear Combination ◽  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
European Parliament ◽  
The State ◽  
Translation Model ◽  
Model Based ◽  
N Gram ◽  
Log Linear

This article describes in detail an n-gram approach to statistical machine translation. This approach consists of a log-linear combination of a translation model based on n-grams of bilingual units, which are referred to as tuples, along with four specific feature functions. Translation performance, which happens to be in the state of the art, is demonstrated with Spanish-to-English and English-to-Spanish translations of the European Parliament Plenary Sessions (EPPS).

scholarly journals Discriminative Word Alignment by Linear Modeling

2010 ◽  
Vol 36 (3) ◽  
pp. 303-339 ◽  
Author(s):  
Yang Liu ◽  
Qun Liu ◽  
Shouxun Lin
Keyword(s):  
State Of The Art ◽  
Statistical Machine Translation ◽  
Generative Models ◽  
Target Language ◽  
Word Alignment ◽  
Alignment Quality ◽  
Linear Modeling ◽  
Parallel Text ◽  
Bilingual Corpora ◽  
Translation Systems

Word alignment plays an important role in many NLP tasks as it indicates the correspondence between words in a parallel text. Although widely used to align large bilingual corpora, generative models are hard to extend to incorporate arbitrary useful linguistic information. This article presents a discriminative framework for word alignment based on a linear model. Within this framework, all knowledge sources are treated as feature functions, which depend on a source language sentence, a target language sentence, and the alignment between them. We describe a number of features that could produce symmetric alignments. Our model is easy to extend and can be optimized with respect to evaluation metrics directly. The model achieves state-of-the-art alignment quality on three word alignment shared tasks for five language pairs with varying divergence and richness of resources. We further show that our approach improves translation performance for various statistical machine translation systems.

scholarly journals Source Language Adaptation Approaches for Resource-Poor Machine Translation

2016 ◽  
Vol 42 (2) ◽  
pp. 277-306 ◽  
Author(s):  
Pidong Wang ◽  
Preslav Nakov ◽  
Hwee Tou Ng
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Source Language ◽  
World Languages ◽  
Word Level ◽  
Resource Poor ◽  
Morphological Variants ◽  
Cross Lingual ◽  
Translation Systems

Most of the world languages are resource-poor for statistical machine translation; still, many of them are actually related to some resource-rich language. Thus, we propose three novel, language-independent approaches to source language adaptation for resource-poor statistical machine translation. Specifically, we build improved statistical machine translation models from a resource-poor language POOR into a target language TGT by adapting and using a large bitext for a related resource-rich language RICH and the same target language TGT. We assume a small POOR–TGT bitext from which we learn word-level and phrase-level paraphrases and cross-lingual morphological variants between the resource-rich and the resource-poor language. Our work is of importance for resource-poor machine translation because it can provide a useful guideline for people building machine translation systems for resource-poor languages. Our experiments for Indonesian/Malay–English translation show that using the large adapted resource-rich bitext yields 7.26 BLEU points of improvement over the unadapted one and 3.09 BLEU points over the original small bitext. Moreover, combining the small POOR–TGT bitext with the adapted bitext outperforms the corresponding combinations with the unadapted bitext by 1.93–3.25 BLEU points. We also demonstrate the applicability of our approaches to other languages and domains.

Query Rewriting Using Monolingual Statistical Machine Translation

2010 ◽  
Vol 36 (3) ◽  
pp. 569-582 ◽  
Author(s):  
Stefan Riezler ◽  
Yi Liu
Keyword(s):  
Machine Translation ◽  
Query Expansion ◽  
Web Search ◽  
Query Language ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Translation Model ◽  
User Query ◽  
Query Logs

Long queries often suffer from low recall in Web search due to conjunctive term matching. The chances of matching words in relevant documents can be increased by rewriting query terms into new terms with similar statistical properties. We present a comparison of approaches that deploy user query logs to learn rewrites of query terms into terms from the document space. We show that the best results are achieved by adopting the perspective of bridging the “lexical chasm” between queries and documents by translating from a source language of user queries into a target language of Web documents. We train a state-of-the-art statistical machine translation model on query-snippet pairs from user query logs, and extract expansion terms from the query rewrites produced by the monolingual translation system. We show in an extrinsic evaluation in a real-world Web search task that the combination of a query-to-snippet translation model with a query language model achieves improved contextual query expansion compared to a state-of-the-art query expansion model that is trained on the same query log data.

scholarly journals Source-Side Discontinuous Phrases for Machine Translation: A Comparative Study on Phrase Extraction and Search

2013 ◽  
Vol 99 (1) ◽  
pp. 17-38
Author(s):  
Matthias Huck ◽  
Erik Scharwächter ◽  
Hermann Ney
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Search Algorithm ◽  
Statistical Machine Translation ◽  
Empirical Evaluation ◽  
Training Data ◽  
Beam Search ◽  
Phrase Extraction ◽  
System Configurations ◽  
Translation Systems

Abstract Standard phrase-based statistical machine translation systems generate translations based on an inventory of continuous bilingual phrases. In this work, we extend a phrase-based decoder with the ability to make use of phrases that are discontinuous in the source part. Our dynamic programming beam search algorithm supports separate pruning of coverage hypotheses per cardinality and of lexical hypotheses per coverage, as well as coverage constraints that impose restrictions on the possible reorderings. In addition to investigating these aspects, which are related to the decoding procedure, we also concentrate our attention on the question of how to obtain source-side discontinuous phrases from parallel training data. Two approaches (hierarchical and discontinuous extraction) are presented and compared. On a large-scale Chinese!English translation task, we conduct a thorough empirical evaluation in order to study a number of system configurations with source-side discontinuous phrases, and to compare them to setups which employ continuous phrases only.

Analysis Accuracy of Similar Word Based Clustering (EWSB) Algorithm on Machine Translator Bahasa Indonesia-Minang

2018 ◽  
Vol 3 (3) ◽  
Author(s):  
Herry Sujaini
Keyword(s):  
Machine Translation ◽  
Clustering Algorithm ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Word Similarity ◽  
Similar Word ◽  
Word Clustering ◽  
Translation Accuracy ◽  
Bahasa Indonesia

Extended Word Similarity Based (EWSB) Clustering is a word clustering algorithm based on the value of words similarity obtained from the computation of a corpus. One of the benefits of clustering with this algorithm is to improve the translation of a statistical machine translation. Previous research proved that EWSB algorithm could improve the Indonesian-English translator, where the algorithm was applied to Indonesian language as target language.This paper discusses the results of a research using EWSB algorithm on a Indonesian to Minang statistical machine translator, where the algorithm is applied to Minang language as the target language. The research obtained resulted that the EWSB algorithm is quite effective when used in Minang language as the target language. The results of this study indicate that EWSB algorithm can improve the translation accuracy by 6.36%.

Sign in / Sign up

Export Citation Format

Share Document