Peter E Brown Stephen A. Della Pietra Fredrick Jelinek Robert L. Mercer John Cocke Vincent J. Della Pietra John D. Lafferty Paul S. Roossin In Section 6 of "A statistical approach to machine translation" (Computational Linguistics 16(2), 79-85), we reported the results of two experiments in which we estimated parameters of a statistical model of translation from English to French.

In the first experiment, the English and French vocabularies each consisted of 9,000 common words, and the model parameters were estimated from 40,000 pairs of sentences 25 words or less in length. Words outside the 9,000-word vocabularies in these sentences were mapped to special unknown words.

In the second experiment, he vocabularies were limited to 1,000 common English words and 1,700 common French words, and the model parameters were estimated from 117,000 pairs of sentences 10 words or less in length that were completely covered by the respective vocabularies.

In Figures 4, 5, and 6 of the paper, we erroneously presented parameter estimates from the 1,000-word experiment, while claiming in the text that they were from the 9,000-word experiment. The parameter estimates for these two experiments differ considerably because of the restriction of the training corpus in the 1,000-word experiment to short, covered sentences. For example, the probability that hear is translated as bravo French le la les \]' ce il Figure 4 Probabilites for the. (~) 1991 Association for Computational Linguistics English: the Probability Fertility Probability 1 .443 .856 .207 .140 .184 .097 .018 .012 Computational Linguistics Volume 17, Number 3 English: not French ne pas non rein Figure 5 Probabilities for not. Probability Fertility

.482 2

.455 0

.029 1

.012 Probability

.728

.153

.114 English: hear French Probability Fertility Probability bravo entendre entendu entends entendons Figure 6 Probabilities for hear. is .992 in the 1,000-word experiment (see Figure 6 of the paper) 1, while it is only .808 in the 9,000-word experiment (see Figure 6 above). This difference is due to the fact that the sentence pair (Hear, hear! \[ Bravo!) is extremely common in our data and is completely covered by the 1,000-word and 1,700-word vocabularies.

Figures 4, 5, and 6 contain the parameter estimates from the 9,000-word experiment. Only probabilities greater than or equal to .01 are reported. .808 .527 .079 .472 .026 .024 .013