A Maximum Entropy Approach to Natural Language Processing

5.4 Word reordering

1. How was maximum entropy used for French NOUN de NOUN phrases?
   To predict whether the English translation swaps the nouns and drops de (taux d’intérêt → interest rate) or translates word for word (conflit d’intérêt → conflict of interest), using features on the left noun, the right noun, or both; it beat a baseline that never swaps.
   • Berger et al., 1996, A Maximum Entropy Approach to Natural Language Processing (Computational Linguistics), §5.4
2. Why are features on both nouns needed in the NOUN de NOUN model?
   Some decisions depend on the pair: phrases ending in intérêt can go either way (conflit d’intérêt vs taux d’intérêt), and some, like taux d’inflation, can translate either way (inflation rate or rate of inflation).
   • Berger et al., 1996, A Maximum Entropy Approach to Natural Language Processing (Computational Linguistics), §5.4