A Statistical Approach to Language Translation

By Peter F. Brown, John Cocke, Stephen Della Pietra, V. D. Pietra, Frederick Jelinek, Robert L. Mercer, Paul S. Roossin. 1988

An approach to automatic translation is outlined that utilizes techniques of statistical information extraction from large data bases. The method is based on the availability of pairs of large corresponding texts that are translations of each other. In our case, the texts are in English and French.Fundamental to the technique is a complex glossary of correspondence of fixed locutions. The steps of the proposed translation process are: (1) Partition the source text into a set of fixed locutions. (2) Use the glossary plus contextual information to select the corresponding set of fixed locutions into a sequence forming the target sentence. (3) Arrange the words of the target fixed locutions into a sequence forming the target sentence.We have developed statistical techniques facilitating both the automatic creation of the glossary, and the performance of the three translation steps, all on the basis of an alignment of corresponding sentences in the two texts.While we are not yet able to provide examples of French / English translation, we present some encouraging intermediate results concerning glossary creation and the arrangement of target word sequences.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016, background): “Neural Machine Translation (NMT) [41, 2] has recently been introduced as a promising approach with the potential of addressing many shortcomings of traditional machine translation systems.”
Datasets: A Community Library for Natural Language Processing (2021, methodology): “…new dataset paradigms have been crucial for driving the development of NLP, from the Hansard corpus for statistical machine translation (Brown et al., 1988) to the Penn Treebank for syntactic modeling (Marcus et al., 1993) to projects like OPUS and Universal Dependencies (Nivre et al.,…”
The Mathematics of Statistical Machine Translation: Parameter Estimation (1993, background): “In recent papers, Brown et al. (1988, 1990) propose a statistical approach to machine translation from French to English.”
Aligning Sentences in Parallel Corpora (1991, background): “Recent work by Brown et al., Brown et al., 1988, Brown et al., 1990 has quickened anew the long dormant idea of using statistical techniques to carry out machine translation from one natural language to another.”
Models of translation equivalence among words (2000, methodology): “Brown et al. (1988) introduced the idea that this correlation can be encoded in translation model parameters.”
A Pendulum Swung too Far (2011, methodology): “(2008), the shift started in 1988 with Brown et al. (1988) and Church (1988). Hall et al. (2008) came to this conclusion based on an analysis of the ACL Anthology, a collection of 16,500 published papers in Computational Linguistics from the 1970s to the”