id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_zv5hinl2kzfuzlpf37agkaqtpq	Najlah Gali	Using linguistic features to automatically extract web page title	2017	28	.pdf	application/pdf	12281	1373	74	Please cite this article as: Najlah Gali , Radu Mariescu Istodor , Pasi Fränti , Using Linguistic Features to Automatically Extract Web page Title, Expert Systems With Applications (2017), doi: Using Linguistic Features to Automatically Extract Web page Title Abstract Existing methods for extracting titles from HTML web page mostly rely on visual and structural features. morphosyntactic characteristics of known titles and define a part-of-speech tag patterns that help to extract candidate phrases However, the modern web page design allows the title to appear as a part of other phrases in the text node of the features: syntactic structure, similarity with the link of the web page, appearance in the title tag, appearance in meta tags, In both tree representations, existing methods use the entire text of the leaf nodes as candidate titles. We have proposed a new method to extract the title from HTML web pages using text segmentation, statistical features of the 	./cache/work_zv5hinl2kzfuzlpf37agkaqtpq.pdf	./txt/work_zv5hinl2kzfuzlpf37agkaqtpq.txt