nltk.IBMModel4¶

class nltk.IBMModel4(sentence_aligned_corpus, iterations, source_word_classes, target_word_classes, probability_tables=None)[source]¶

Translation model that reorders output words based on their type and their distance from other related words in the output sentence

>>> bitext = []
>>> bitext.append(AlignedSent(['klein', 'ist', 'das', 'haus'], ['the', 'house', 'is', 'small']))
>>> bitext.append(AlignedSent(['das', 'haus', 'war', 'ja', 'groß'], ['the', 'house', 'was', 'big']))
>>> bitext.append(AlignedSent(['das', 'buch', 'ist', 'ja', 'klein'], ['the', 'book', 'is', 'small']))
>>> bitext.append(AlignedSent(['ein', 'haus', 'ist', 'klein'], ['a', 'house', 'is', 'small']))
>>> bitext.append(AlignedSent(['das', 'haus'], ['the', 'house']))
>>> bitext.append(AlignedSent(['das', 'buch'], ['the', 'book']))
>>> bitext.append(AlignedSent(['ein', 'buch'], ['a', 'book']))
>>> bitext.append(AlignedSent(['ich', 'fasse', 'das', 'buch', 'zusammen'], ['i', 'summarize', 'the', 'book']))
>>> bitext.append(AlignedSent(['fasse', 'zusammen'], ['summarize']))
>>> src_classes = {'the': 0, 'a': 0, 'small': 1, 'big': 1, 'house': 2, 'book': 2, 'is': 3, 'was': 3, 'i': 4, 'summarize': 5 }
>>> trg_classes = {'das': 0, 'ein': 0, 'haus': 1, 'buch': 1, 'klein': 2, 'groß': 2, 'ist': 3, 'war': 3, 'ja': 4, 'ich': 5, 'fasse': 6, 'zusammen': 6 }

>>> ibm4 = IBMModel4(bitext, 5, src_classes, trg_classes)

>>> print(round(ibm4.translation_table['buch']['book'], 3))
1.0
>>> print(round(ibm4.translation_table['das']['book'], 3))
0.0
>>> print(round(ibm4.translation_table['ja'][None], 3))
1.0

>>> print(round(ibm4.head_distortion_table[1][0][1], 3))
1.0
>>> print(round(ibm4.head_distortion_table[2][0][1], 3))
0.0
>>> print(round(ibm4.non_head_distortion_table[3][6], 3))
0.5

>>> print(round(ibm4.fertility_table[2]['summarize'], 3))
1.0
>>> print(round(ibm4.fertility_table[1]['book'], 3))
1.0

>>> print(ibm4.p1)
0.033...

>>> 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, None), (4, 3)])