<div>Respected Readers,</div>
<div>The need to create a Gold Standard Alignment of vital importance when one has to evaluate results of bilingual corpus given to <strong>word alignment</strong> tools like Giza++. This Gold Standard Alignment( Test Data ) as many of us know serves as a reference against which one can evaluate the results obtained using the Training data. For the creation of this test data which is a subset of the Training Data, when one goes about it manually, an individual comes across lot of variations with respect source and target languages while aligning words for e.g </div>
<div> </div>
<div><span lang="">
<p>1# 5 # does(1) he(2) go(3) home(4) ?(5) # 4 2 4 3 0 </p>
<p>1# 5 # <font face="Mangal" size="2"><font face="Mangal" size="2">क्या(1) वह(2) घर(3) जाता(4) है(5) # </font></font></p></span><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="EN">0</span></font></font><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang=""> 2 4 3 0 </span></font></font>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="">the word "does" maps to 'ता' of 'जाता' </span></font></font></p>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="">There are many such careful considerations one has to keep in mind while going about creation of Gold Standard Alignment.</span></font></font></p>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="">Could you please suggest me any basic guidelines( if not English-Hindi language specific ) that one could follow while going about this, any reference paper or advice would be of great help.</span></font></font></p>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="">Thanking You</span></font></font></p>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang="">Mohnish</span></font></font></p>
<p><font face="Mangal" size="2"><font face="Mangal" size="2"><span lang=""> </span></font></font></p></div>