Question Statement: [20]
How the Arabic parsing investigated by comparing the lexicalised and unlexicalised parsers? What is the relation of ATB, SBJ, OBJ and PRD functional tags in this parsing? |
Read more: CS606 Assignment 5 solution - Virtual University of Pakistan http://vustudents.ning.com/group/cs606compilerconstruction/forum/topics/cs606-assignment-5-solution#ixzz1k4hrOT44
Arabic Penn Treebank (ATB): The Penn Arabic Treebank (Maamouri and Bies 2004) is a corpus of 23,611 parse-annotated sentences from Arabic newswire text in Modern Standard Arabic (MSA). The ATB is a fine-grained corpus, its annotation includes 22 phrasal tags, 20 individual functional tags and 24 basic POS-tags1 (with a total of 497 different POS tags with morpholog- ical information). In addition, the ATB involves empty nodes to capture pro-drop as well as non-local dependen- cies (NLDs). The full POS tagset with morphological in- formation indicates case, mood, gender, definiteness, etc. The ATB treebank contains a set of labels (called functional tags or functional labels) associated with func- tional information, such as -SBJ for ‘subject’ and -OBJ for ‘object’ -PRD for predicate |
Read more: CS606 Assignment 5 solution - Virtual University of Pakistanhttp://vustudents.ning.com/group/cs606compilerconstruction/forum/topics/cs606-assignment-5-solution#ixzz1k4i7NSew
No comments:
Post a Comment