A Method for Proper Noun Extraction in Kurdish.
Hossein Hassani.
Publisher: SLATE, 2017.
This paper suggests a method for proper noun identification in Kurdish texts. Kurdish proper nouns are not capitalized and they also assume other part-of-speech roles, which leads to a broad ambiguity that should be addressed in Kurdish proper noun recognition applications. Kurdish is also among less-resourced languages. We developed an application based on an architecture which includes a number of name lists, a set of rules, and a set of processes that recognizes Kurdish person names. This can help the study of Information Retrieval (IR) in Kurdish to advance and can also be used in Kurdish machine translation. We conducted several experiments which showed that the precision of the method is more than 95%, the recall is between 40% to 80%, and the F-measure is close to 60% to more than 80%. The reason for the low recall precision was because our name lists were not exhaustive enough to cover the vast majority of the Kurdish names. [1]
=KTML_Link_External_Begin=https://www.kurdipedia.org/docviewer.aspx?id=445067&document=0001.PDF=KTML_Link_External_Between= Click to read the article: A Method for Proper Noun Extraction in Kurdish=KTML_Link_External_End=
کوردیپێدیا بەرپرس نییە لە ناوەڕۆکی ئەم تۆمارە و خاوەنەکەی لێی بەرپرسیارە. کوردیپێدیا بە مەبەستی ئەرشیڤکردن تۆماری کردووە.
ئەم بابەتە بەزمانی (English) نووسراوە، کلیک لە ئایکۆنی
بکە بۆ کردنەوەی بابەتەکە بەو زمانەی کە پێی نووسراوە!
This item has been written in (English) language, click on icon
to open the item in the original language!
ئەم بابەتە 512 جار بینراوە
ڕای خۆت دەربارەی ئەم بابەتە بنووسە!