Dear All,<br><br>Do we really need to add <s> at the start of each sentence and </s> at the end of each sentence for the preparation of a language model using ngram-count.<br><br>my data looks like:<br><br>=============<br>
<s> sentnce1 </s><br><s> sentence2 </s><br>so on...<br>=============<br><br>De we really need <s> and </s> tags?<br><br>thank you in advance,<br clear="all"><br>-- <br>---<br>M G Abbas Malik<br>
Doctorant (PhD Student)<br>Université Joseph Fourier,<br>Groupe d'Etude pour la Traduction Automatique et le Traitement Automatisé des Langues et de la Parole (GETALP)<br>Laboratoire d'Informatique de Grenoble (LIG) / Grenoble Informatics Laboratory<br>
<br>GETALP, LIG-Campus, BP53<br>385 Rue de la Bibliothèque,<br>38041 Grenoble Cedex 9, France<br>Off: +33 (0)4 76 51 48 17<br>Mob: +33 (0)6 74 50 46 01<br>e-mail: abbas.malik at <a href="http://imag.fr">imag.fr</a> abbas.malik at <a href="http://gmail.com">gmail.com</a><br>
URL: <a href="http://www.puran.info">www.puran.info</a><br>