| other,2-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4602 We approximateArabic 's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
| model,8-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4608 We approximate Arabic's rich morphology by amodel that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
| other,11-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4611 We approximate Arabic's rich morphology by a model that aword consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
| other,17-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4617 We approximate Arabic's rich morphology by a model that a word consists of a sequence ofmorphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
| other,20-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4620 We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in thepattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
| other,21-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4621 We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the patternprefix * - stem-suffix * (* denotes zero or more occurrences of a morpheme). |
| other,35-1-P03-1051,bq | We approximate <term> Arabic 's rich morphology </term> by a <term> model </term> that a <term> word </term> consists of a sequence of <term> morphemes </term> in the <term> pattern </term><term> prefix * - stem-suffix * </term> ( * denotes zero or more occurrences of a <term> morpheme </term> ) . | #4635 We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of amorpheme). |
| lr,7-2-P03-1051,bq | Our method is seeded by a small <term> manually segmented Arabic corpus </term> and uses it to bootstrap an <term> unsupervised algorithm </term> to build the <term> Arabic word segmenter </term> from a large <term> unsegmented Arabic corpus </term> . | #4645 Our method is seeded by a smallmanually segmented Arabic corpus and uses it to bootstrap an unsupervised algorithm to build the Arabic word segmenter from a large unsegmented Arabic corpus. |
| tech,17-2-P03-1051,bq | Our method is seeded by a small <term> manually segmented Arabic corpus </term> and uses it to bootstrap an <term> unsupervised algorithm </term> to build the <term> Arabic word segmenter </term> from a large <term> unsegmented Arabic corpus </term> . | #4655 Our method is seeded by a small manually segmented Arabic corpus and uses it to bootstrap anunsupervised algorithm to build the Arabic word segmenter from a large unsegmented Arabic corpus. |
| tech,22-2-P03-1051,bq | Our method is seeded by a small <term> manually segmented Arabic corpus </term> and uses it to bootstrap an <term> unsupervised algorithm </term> to build the <term> Arabic word segmenter </term> from a large <term> unsegmented Arabic corpus </term> . | #4660 Our method is seeded by a small manually segmented Arabic corpus and uses it to bootstrap an unsupervised algorithm to build theArabic word segmenter from a large unsegmented Arabic corpus. |
| lr,28-2-P03-1051,bq | Our method is seeded by a small <term> manually segmented Arabic corpus </term> and uses it to bootstrap an <term> unsupervised algorithm </term> to build the <term> Arabic word segmenter </term> from a large <term> unsegmented Arabic corpus </term> . | #4666 Our method is seeded by a small manually segmented Arabic corpus and uses it to bootstrap an unsupervised algorithm to build the Arabic word segmenter from a largeunsegmented Arabic corpus. |
| tech,1-3-P03-1051,bq | The <term> algorithm </term> uses a <term> trigram language model </term> to determine the most probable <term> morpheme sequence </term> for a given <term> input </term> . | #4671 Thealgorithm uses a trigram language model to determine the most probable morpheme sequence for a given input. |
| model,4-3-P03-1051,bq | The <term> algorithm </term> uses a <term> trigram language model </term> to determine the most probable <term> morpheme sequence </term> for a given <term> input </term> . | #4674 The algorithm uses atrigram language model to determine the most probable morpheme sequence for a given input. |
| other,12-3-P03-1051,bq | The <term> algorithm </term> uses a <term> trigram language model </term> to determine the most probable <term> morpheme sequence </term> for a given <term> input </term> . | #4682 The algorithm uses a trigram language model to determine the most probablemorpheme sequence for a given input. |
| other,17-3-P03-1051,bq | The <term> algorithm </term> uses a <term> trigram language model </term> to determine the most probable <term> morpheme sequence </term> for a given <term> input </term> . | #4687 The algorithm uses a trigram language model to determine the most probable morpheme sequence for a giveninput. |
| model,1-4-P03-1051,bq | The <term> language model </term> is initially estimated from a small <term> manually segmented corpus </term> of about 110,000 <term> words </term> . | #4690 Thelanguage model is initially estimated from a small manually segmented corpus of about 110,000 words. |
| lr,9-4-P03-1051,bq | The <term> language model </term> is initially estimated from a small <term> manually segmented corpus </term> of about 110,000 <term> words </term> . | #4698 The language model is initially estimated from a smallmanually segmented corpus of about 110,000 words. |
| other,15-4-P03-1051,bq | The <term> language model </term> is initially estimated from a small <term> manually segmented corpus </term> of about 110,000 <term> words </term> . | #4704 The language model is initially estimated from a small manually segmented corpus of about 110,000words. |
| tech,3-5-P03-1051,bq | To improve the <term> segmentation </term><term> accuracy </term> , we use an <term> unsupervised algorithm </term> for automatically acquiring new <term> stems </term> from a 155 million <term> word </term><term> unsegmented corpus </term> , and re-estimate the <term> model parameters </term> with the expanded <term> vocabulary </term> and <term> training corpus </term> . | #4709 To improve thesegmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus. |
| measure(ment),4-5-P03-1051,bq | To improve the <term> segmentation </term><term> accuracy </term> , we use an <term> unsupervised algorithm </term> for automatically acquiring new <term> stems </term> from a 155 million <term> word </term><term> unsegmented corpus </term> , and re-estimate the <term> model parameters </term> with the expanded <term> vocabulary </term> and <term> training corpus </term> . | #4710 To improve the segmentationaccuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus. |
