Franz Josef Och

Learn More
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models outperform word-based models. Our empirical results, which hold(More)
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(More)
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.(More)
We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible hidden variables.(More)
This paper reports on the benefits of largescale statistical language modeling in machine translation. A distributed infrastructure is proposed which we use to train on up to 2 trillion tokens, resulting in language models having up to 300 billion n-grams. It is capable of providing smoothed probabilities for fast, single-pass decoding. We introduce a new(More)
In this paper, we describe improved alignment models for statistical machine translation. The statistical translation approach uses two types of information: a translation model and a language model. The language model used is a bigram or general m-gram model. The translation model is decomposed into a lexical and an alignment model. We describe two(More)
In this paper we present a tool for the evaluation of translation quality. First, the typical requirements of such a tool in the framework of machine translation (MT) research are discussed. We define evaluation criteria which are more adequate than pure edit distance and we describe how the measurement along these quality criteria is performed(More)
In this paper, we t)resent and compare various alignnmnt models for statistical machine translation. We propose to measure tile quality of an aligmnent model using the quality of the Viterbi alignment comt)ared to a manually-produced alignment and describe a refined mmotat ion scheme to produce suitable reference alignments. We also con,pare the impact of(More)