[PDF][PDF] Learning hash functions for cross-view similarity search

S Kumar, R Udupa - Twenty-second international joint conference on …, 2011 - ijcai.org
Many applications in Multilingual and Multimodal Information Access involve searching
large databases of high dimensional data objects with multiple (conditionally independent) …

A survey of query auto completion in information retrieval

F Cai, M De Rijke - Foundations and Trends® in Information …, 2016 - nowpublishers.com
In information retrieval, query auto completion (QAC), also known as typeahead [Xiao et al.,
2013, Cai et al., 2014b] and auto-complete suggestion [Jain and Mishne, 2010], refers to the …

A survey on text mining in social networks

R Irfan, CK King, D Grages, S Ewen… - The Knowledge …, 2015 - cambridge.org
In this survey, we review different text mining techniques to discover various textual patterns
from the social networking sites. Social network applications create opportunities to …

Arabizi detection and conversion to Arabic

K Darwish - arXiv preprint arXiv:1306.6755, 2013 - arxiv.org
Arabizi is Arabic text that is written using Latin characters. Arabizi is used to present both
Modern Standard Arabic (MSA) or Arabic dialects. It is commonly used in informal settings …

Terrorism, social media and text mining technique: Review of six years past studies

TM Kibtiah, E Miranda, Y Fernando… - 2020 International …, 2020 - ieeexplore.ieee.org
The aim of this paper is to examine the Islamic State of Iraq and Syria (ISIS) recruitment
actual behavior through social media. The ISIS has targeted Indonesia as the main source of …

[PDF][PDF] Two-stage hashing for fast document retrieval

H Li, W Liu, H Ji - Proceedings of the 52nd Annual Meeting of the …, 2014 - aclanthology.org
This work fulfills sublinear time Nearest Neighbor Search (NNS) in massivescale document
collections. The primary contribution is to propose a two-stage unsupervised hashing …

[PDF][PDF] Improved transliteration mining using graph reinforcement

A El Kahki, K Darwish, AS El Din… - Proceedings of the …, 2011 - aclanthology.org
Mining of transliterations from comparable or parallel text can enhance natural language
processing applications such as machine translation and cross language information …

Enriched search features based in part on discovering people-centric search intent

A Ray, D Meyerzon, UR Udupa - US Patent 8,510,322, 2013 - Google Patents
(57) ABSTRACT A search environment of an embodiment includes name min ing and
matching features used in part to identify people centric queries and provide an enriched …

Inlook: Revisiting email search experience

P Ramarao, S Iyengar, P Chitnis, R Udupa… - Proceedings of the 39th …, 2016 - dl.acm.org
Emails continue to remain the most important and widely used mode of online
communication despite having its origins in the middle of last century and being threatened …

Hybrid matching algorithm for personal names

C Varol, C Bayrak - Journal of Data and Information Quality (JDIQ), 2012 - dl.acm.org
Companies acquire personal information from phone, World Wide Web, or email in order to
sell or send an advertisement about their product. However, when this information is …