Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

Statistical approaches to processing natural language text have become dominant in recent years This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear The book contains all the theory and algorithms needed for building NLP tools It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, and other applications

/pdf/foundations-of-statistical-natural-language-processing-1ou5e6c2q6.pdf

Foundations of Statistical Natural Language Processing

We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

/pdf/moses-open-source-toolkit-for-statistical-machine-3pmfuwk8uc.pdf

Moses: Open Source Toolkit for Statistical Machine Translation

We present and compare various methods for computing word alignments using statistical or heuristic models. We consider the five alignment models presented in Brown, Della Pietra, Della Pietra, and Mercer (1993), the hidden Markov alignment model, smoothing techniques, and refinements. These statistical models are compared with two heuristic models based on the Dice coefficient. We present different methods for combining word alignments to perform a symmetrization of directed statistical alignment models. As evaluation criterion, we use the quality of the resulting Viterbi alignment compared to a manually produced reference alignment. We evaluate the models on the German-English Verbmobil task and the French-English Hansards task. We perform a detailed analysis of various design decisions of our statistical alignment system and evaluate these on training corpora of various sizes. An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models. In the Appendix, we present an efficient training algorithm for the alignment models presented.

/pdf/a-systematic-comparison-of-various-statistical-alignment-3pcl3i9uz3.pdf

A systematic comparison of various statistical alignment models

Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training criteria which directly optimize translation quality. These training criteria make use of recently proposed automatic evaluation metrics. We describe a new algorithm for efficient training an unsmoothed error count. We show that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.

Minimum Error Rate Training in Statistical Machine Translation

In this paper, we describe a new model for word alignment in statistical translation and present experimental results. The idea of the model is to make the alignment probabilities dependent on the differences in the alignment positions rather than on the absolute positions. To achieve this goal, the approach uses a first-order Hidden Markov model (HMM) for the word alignment problem as they are used successfully in speech recognition for the time alignment problem. The difference to the time alignment HMM is that there is no monotony constraint for the possible word orderings. We describe the details of the model and test the model on several bilingual corpora.

/pdf/hmm-based-word-alignment-in-statistical-translation-5grpe43xv1.pdf

HMM-based word alignment in statistical translation

Training word alignment models on large corpora is a very time-consuming processes. This paper describes two parallel implementations of GIZA++ that accelerate this word alignment process. One of the implementations runs on computer clusters, the other runs on multi-processor system using multi-threading technology. Results show a near-linear speed-up according to the number of CPUs used, and alignment quality is preserved.

Parallel Implementations of Word Alignment Tool

In this paper, we describe a fast search algorithm for statistical translation based on dynamic programming (DP) and present experimental results. The approach is based on the assumption that the word alignment is monotone with respect to the word order in both languages. To reduce the search e ort for this approach, we introduce two methods: an acceleration technique to e ciently compute the dynamic programming recursion equation and a beam search strategy as used in speech recognition. The experimental tests carried out on the Verbmobil corpus showed that the search space, measured by the number of translation hypotheses, is reduced by a factor of about 230 without a ecting the translation performance.

Accelerated DP based search for statistical translation.

In this paper we present experiments concerning translation model adaptation for statistical machine translation. We develop a method to adapt translation models using in- formation retrieval. The approach selects sentences similar to the test set to form an adapted training corpus. The method allows a better use of additionally available out-of-domain training data or finds in-domain data in a mixed corpus. The adapted translation models significantly improve the translation performance compared to competitive baseline sys- tems.

Adaptation of the Translation Model for Statistical Machine Translation based on Information Retrieval

Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEU and the related NIST metric, are becoming increasingly important in MT. Yet, their behaviors are not fully understood. In this paper, we analyze some flaws in the BLEU/NIST metrics. With a better understanding of these problems, we can better interpret the reported BLEU/NIST scores. In addition, this paper reports a novel method of calculating the confidence intervals for BLEU/NIST scores using bootstrapping. With this method, we can determine whether two MT systems are significantly different from each other.

/pdf/interpreting-bleu-nist-scores-how-much-improvement-do-we-di297zyjxf.pdf

Stephan Vogel

Papers

HMM-based word alignment in statistical translation

Parallel Implementations of Word Alignment Tool

Accelerated DP based search for statistical translation.

Adaptation of the Translation Model for Statistical Machine Translation based on Information Retrieval

Interpreting BLEU/NIST Scores: How Much Improvement do We Need to Have a Better System?