Currently every person’s use short text in real life for communication and chatting purpose. Short texts are also uses in social posts, news titles, events, search queries, tweets, conversations, keywords, Short text understanding is a confusing process in ideas deals with secret messages. The short text is produce that contain social posts, discussions, keywords and news titles which are restricted context and represent the significance of the text or insufficient information. As short text has more than one meaning, they are challenging to understand as they are noisy and ambiguous. The term can be any single or multi-word. Short texts do not contain satisfactory information. Some short texts have unique features. So these short texts are difficult to handle. It essential well understand the short text. Semantic analysis is necessary to understand the short text properly. Tasks such as part-of-speech tagging, concept labelling and segmentation are used for semantic analysis. Conduct short text uses in real life information. The prototype system is constructed and used to recognize the short text. These systems deliver the semantic knowledge from knowledge base and collection of written words that are automatically harvest. Creating construction of co-occurrence network and term extraction showing to better understand for short text.

Short Text, Semantics, Text segmentation, co-occurrence,Term Extraction

[1] M. Utiyama and H. Isahara, “A statistical model for domain-independent text Segmentation,” in Proc. 39th Annu. Meeting Assoc. Comput. Linguistics, 2001, pp. 499–506.
[2] N. Mishra, R. Saha Roy, N. Ganguly, S. Laxman, and M. Choudhury, “Unsupervised query segmentation using only query logs,” in Proc. 20th Int. Conf. Companion WorldWideWeb, 2011, pp. 91–92.
[3] D. Deng, G. Li, and J. Feng, “An efficient Trie-based method for approximate entity extraction with edit-distance constraints,” in Proc. IEEE 28th Int. Conf. Data Eng., 2012, pp. 762–773.
[4] P. Li, H. Wang, K. Q. Zhu, Z. Wang, and X. Wu, “Computing term similarity by large probabilistic ISA Knowledge,” in Proc. 22nd ACM Int. Conf. Inform. #38; Manage., 2013, pp. 1401–1410
[5] W. Hua, Z. Wang, H. Wang, K. Zheng, and X. Zhou, “Short text understanding through lexical-semantic analysis,” in ICDE, pp. 495–506, 2015.
[6] Zheng Yu, Haixun Wang, Xuemin Lin, Senior Member, IEEE, and Min Wang, “Understanding Short Texts through Semantic Enrichment and Hashing”. VOL. 28, NO. 2, FEBRUARY 2016
[7] Wen Hua, Zhongyuan Wang, Haixun Wang, Member, IEEE, Kai Zheng, Member, IEEE, and Xiao Fang Zhou, Senior Member, IEEE, “Understand Short Texts by Harvesting and Analyzing Semantic Knowledge” , VOL. 29, NO. 3, MARCH 2017
[8] E. Brill, “A simple rule-b9ased part of speech tagger,” in Proc. Workshop Speech Natural Language, 1992, pp. 112–116.
[9] R. Weischedel, R. Schwartz, J. Palmucci, M. Meteer, and L. Ramshaw, “Coping with ambiguity and unknown words through probabilistic models,” Comput. Linguistics, vol. 19, no. 2, pp. 361–382, 1993.
[10] https://cracku.in/blog/nicknames-of-indian-states-and-cities-pdf/
[11] http://www.txtdrop.com/abbreviations.php