nltk.IBMModel1¶

class nltk.IBMModel1(sentence_aligned_corpus, iterations, probability_tables=None)[source]¶

Lexical translation model that ignores word order

>>> bitext = []
>>> bitext.append(AlignedSent(['klein', 'ist', 'das', 'haus'], ['the', 'house', 'is', 'small']))
>>> bitext.append(AlignedSent(['das', 'haus', 'ist', 'ja', 'groß'], ['the', 'house', 'is', 'big']))
>>> bitext.append(AlignedSent(['das', 'buch', 'ist', 'ja', 'klein'], ['the', 'book', 'is', 'small']))
>>> bitext.append(AlignedSent(['das', 'haus'], ['the', 'house']))
>>> bitext.append(AlignedSent(['das', 'buch'], ['the', 'book']))
>>> bitext.append(AlignedSent(['ein', 'buch'], ['a', 'book']))

>>> ibm1 = IBMModel1(bitext, 5)

>>> print(ibm1.translation_table['buch']['book'])
0.889...
>>> print(ibm1.translation_table['das']['book'])
0.061...
>>> print(ibm1.translation_table['buch'][None])
0.113...
>>> print(ibm1.translation_table['ja'][None])
0.072...

>>> test_sentence = bitext[2]
>>> test_sentence.words
['das', 'buch', 'ist', 'ja', 'klein']
>>> test_sentence.mots
['the', 'book', 'is', 'small']
>>> test_sentence.alignment
Alignment([(0, 0), (1, 1), (2, 2), (3, 2), (4, 3)])