Statistical machine translation (SMT) treats the translation of natural language as a machine learning problem. By examining many samples of human-produced translation, SMT algorithms automatically learn how to translate. SMT has made tremendous strides in less than two decades, and many popular techniques have only emerged within the last few years. This survey presents a tutorial overview of state-of-the-art SMT at the beginning of 2007. We begin with the context of the current research, and then move to a formal problem description and an overview of the four main subproblems: translational equivalence modeling, mathematical modeling, parameter estimation, and decoding. Along the way, we present a taxonomy of some different approaches within these areas. We conclude with an overview of evaluation and notes on future directions.

Statistical machine translation systems are usually trained on large amounts of bilingual text and monolingual text in the target language. In this paper we explore the use of transductive semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. We propose several algorithms with this aim, and present the strengths and weaknesses of each one. We present detailed experimental evaluations on the French–English EuroParl data set and on data from the NIST Chinese–English largedata track. We show a significant improvement in translation quality on both tasks. 1

We present the PORTAGE statistical machine translation system which participated in the shared task of the ACL 2007 Second Workshop on Statistical Machine Translation. The focus of this description is on improvements which were incorporated into the system over the last year. These include adapted language models, phrase table pruning, an IBM1-based decoder feature, and rescoring with posterior probabilities. 1

Entity extraction is the task of identifying names and nominal phrases (‘mentions’) in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2%relative improvement in name tagging F-measure, representing a 15.0 % error reduction), as well as Chinese to English entity translation (9.1 % relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.

Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery, a standard dataset for this task, our system achieved 66 % accuracy, compared to 80 % of its fully supervised counterpart, demonstrating the promise of unsupervised approaches for this task. 1

The average results obtained by unsupervised statistical parsers have greatly improved in the last few years, but on many specific sentences they are of rather low quality. The output of such parsers is becoming valuable for various applications, and it is radically less expensive to create than manually annotated training data. Hence, automatic selection of high quality parses created by unsupervised parsers is an important problem. In this paper we present PUPA, a POS-based Unsupervised Parse Assessment algorithm. The algorithm assesses the quality of a parse tree using POS sequence statistics collected from a batch of parsed sentences. We evaluate the algorithm by using an unsupervised POS tagger and an unsupervised parser, selecting high quality parsed sentences from English (WSJ) and German (NEGRA) corpora. We show that PUPA outperforms the leading previous parse assessment algorithm for supervised parsers, as well as a strong unsupervised baseline. Consequently, PUPA allows obtaining high quality parses without any human involvement. 1

Abstract not found

We describe an approach to improve Statistical Machine Translation (SMT) performance using multi-lingual, parallel, sentence-aligned corpora in several bridge languages. Our approach consists of a simple method for utilizing a bridge language to create a word alignment system and a procedure for combining word alignment systems from multiple bridge languages. The final translation is obtained by consensus decoding that combines hypotheses obtained using all bridge language word alignments. We present experiments showing that multilingual, parallel text in Spanish, French, Russian, and Chinese can be utilized in this framework to improve translation performance on an Arabic-to-English task. 1

A novel and robust approach to improving statistical machine translation fluency is developed within a minimum Bayesrisk decoding framework. By segmenting translation lattices according to confidence measures over the maximum likelihood translation hypothesis we are able to focus on regions with potential translation errors. Hypothesis space constraints based on monolingual coverage are applied to the low confidence regions to improve overall translation fluency. 1

Statistical machine translation (SMT) models need large bilingual corpora for training, which are unavailable for some language pairs. This paper provides the first serious experimental study of active learning for SMT. We use active learning to improve the quality of a phrase-based SMT system, and show significant improvements in translation compared to a random sentence selection baseline, when test and training data are taken from the same or different domains. Experimental results are shown in a simulated setting using three language pairs, and in a realistic situation for Bangla-English, a language pair with limited translation resources.