<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2156">
  <Title>Decision-Tree based Error Correction for Statistical Phrase Break Prediction in Korean *</Title>
  <Section position="5" start_page="1052" end_page="1053" type="evalu">
    <SectionTitle>
4 Experimental Results
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="1052" end_page="1052" type="sub_section">
      <SectionTitle>
4.1 Corpus
</SectionTitle>
      <Paragraph position="0"> The, experiments are t)ertbrmed on a Korean news story database,, called MBCNF, WS\])I~, of spoken Korean directly recorded from broadcasting news. The size of th(; database is now 6,111 sentences (75,647 words) and it is eontinnously growing. '12) lm used in the phrase break prediction experiments, |;tie database has been POS tagged and break-b~beled with major and minor phrase breaks.</Paragraph>
    </Section>
    <Section position="2" start_page="1052" end_page="1053" type="sub_section">
      <SectionTitle>
4.2 Phrase Break Detection and Error
Correction
</SectionTitle>
      <Paragraph position="0"> We, I)eribrmed three experiments to show synergistic results of probabilistic method and tree-based error correction method. First, only probabilistic method was used to predict phrase breaks. %'igrams, bigrams and unigrams for phrase break prediction were trained fl:om the break-labeled an(1 POS tagged 5,492 sentences of the MBCNEWSDB by adjusting the POS sequences of words as described in sut)section 3.1.2. The other 619 sentences are used to test the t)ertbrnum(:e of the probabilistic I)hrase break predictor. In the second experiment, we made a decision tree, which can be used only to predict phrase breaks and cannot be used to  correct phrase breaks, from the 5,429 sentences. Also the 619 sentences were used to test the performance of the decision tree-based phrase break predictor. The size of feature vector (the size of the window) is w~ried fi'om 7 (the POS tag of current word, preceding 3 words and following 3 words) to 15 (the POS tag of current word, preceding 7 words and following 7 words).</Paragraph>
      <Paragraph position="1"> The third experiment utilized a decision tree as post error corrector as presented in this paper.</Paragraph>
      <Paragraph position="2"> We trained trigrams, bigrams and unigrams using 60% of totM sentences, and learned the decision tree using 3(1% of total sentences. For the other experiment, 50% aim 40% of total senfences are used tbr probability training and tbr decision tree learning, respectively. Tim other 10% of total sentences were used to test as in the prevkms ext)eriments(Figure 3). For the decision tree in the tlfird experiment, though the size of the window is also varied from 7 words to 15 words, the size of feature vector is varied from 14 to 30 because phrase breaks tagged by probabilistic predictor are include in the feature  the test in the experiments.</Paragraph>
      <Paragraph position="3"> Tit(; performance is assessed with reference to N, the total number of junctures (spaces in text including any type of phrase breaks), and B, the total number of phrase breaks (only minor(b1) and major(b,)) breaks) in the test set. The errors can be divided into insertions, deletions and substitutions. An insertion (I) is a break inserted in the test sentence, where there is not a break in the reference sentence. A deletion (D) occurs when a break is marked in the rethrence sentence but not in the test sentence. A substitution (S) is an error between major break and minor break or vice versa. Since there is no single way to measure the performance of phrase break prediction, we use the following peribrmance measures (Taylor and Black, 1998).</Paragraph>
      <Paragraph position="5"> We use another pertbrmance nmasure, cMled adjusted score, which refer to the prediction accuracy in proportion to the total nmnber of phrase breaks as following performance measure proposed by Sanders (Sanders, 1995).</Paragraph>
      <Paragraph position="6"> Adjusted_Score - ,IC - NB 1-NI3 ' where NB 1 means the proportion of no breaks to the number of interword spaces and ,lC means the Juncture_Correct/lO0.</Paragraph>
      <Paragraph position="7"> Table 1. shows the experimental results of our phrase break prediction and error con:ection method on the 619 open test sentences (10% of the total corpus). In the table, W means the thature vector size tbr the decision tree, and 6:3 and 4:5 mean ratio of the number of sentences used in the probabilistic train and the decision tree induction.</Paragraph>
      <Paragraph position="8"> The performance of probabilistic method is better than that of IG-tree method with any window size in U'reak_Cor'rect. However, as the ti;ature vector size is growing in IO-tree method, .lv, nctv, re_Co'rrect and Adj,(sled_Score become better than those of the l)robM)ilitic method.</Paragraph>
      <Paragraph position="9"> From the fact that the attribute located in the first level of the decision trees is the POS tag of preceding word, we can see that the POS tag of preceding word iv the most useful attribute for predicting phrase breaks.</Paragraph>
      <Paragraph position="10"> The pertbrmance before the error correction in hyl)rid experiments iv worse ttlan that of the original 1)robabilistic method because the size of training corlms for probabilistic method is only 66.6% and 44.4:% of that of the original one, respectively. However, the performance sets improved by the post error correction tree, and becorns finally higher than that of both the probabilistic nmthod and the IG-tree method. The attribute located in the first level of the decision tree is the phrase break that was predicted in the probatfilistic method phase. Although the initial pertbrmmme (beibre error correction) of the exImriment using 4:5 corpus ratio is worse than that of the experiment using 6:3 corlms ratio, the final perfbrmance gets impressively improved as the decision tree induction corpus  incre,~ses from 30% 1;o 50% of the to|;al (:()rims. ~l)his result; shows t;h~t |;he prol)osed ~rehilx~eture c~m 1)rovi(te, improved results evell with the phrase 1)re~k \])re(tie|:or |:h~l; h~s I)oor |nit|a,1 perf()z'51 I~L51(;(~,.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>