Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Furkan Şahinuç"'
Publikováno v:
Signal, Image and Video Processing
Hate speech against individuals or communities with different backgrounds is a major problem in online social networks. The domain of hate speech has spread to various topics, including race, religion, and gender. Although there are many efforts for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b8ced97d9b02d123d3d698b67e341cb
https://hdl.handle.net/11693/111608
https://hdl.handle.net/11693/111608
Publikováno v:
Social Network Analysis and Mining. 12
Information is spread as individuals engage with other users in the underlying social network. Analysis of social engagements can therefore provide insights to understand the motivation behind how and why users engage with others in different activit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e841eebe966e0bac184886bc9a4c8e4
https://doi.org/10.1007/s13278-022-00872-1
https://doi.org/10.1007/s13278-022-00872-1
Publikováno v:
Natural Language Engineering
Word embeddings have become important building blocks that are used profoundly in natural language processing (NLP). Despite their several advantages, word embeddings can unintentionally accommodate some gender- and ethnicity-based biases that are pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd3f44896156426fe16a9c102217712f
https://hdl.handle.net/11693/111389
https://hdl.handle.net/11693/111389
Publikováno v:
Information Processing & Management
We propose bidirectional imparting or BiImp, a generalized method for aligning embedding dimensions with concepts during the embedding learning phase. While preserving the semantic structure of the embedding space, BiImp makes dimensions interpretabl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cdaa2f425ace64a800a0774668215cae
https://hdl.handle.net/11693/111493
https://hdl.handle.net/11693/111493
Publikováno v:
SIU
Microblogs are short and irregular texts in which people express their opinions in social media. While classification of social media microblog texts according to their topics constitutes a semantic substructure, it helps implementation of various ap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa25cb6dcb20f622f074d2234e041e67
https://doi.org/10.1109/siu53274.2021.9477781
https://doi.org/10.1109/siu53274.2021.9477781
After George Floyd's death in May 2020, the volume of discussion in social media increased dramatically. A series of protests followed this tragic event, called as the 2020 BlackLivesMatter movement. Eventually, many user accounts are deleted by thei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d8dad175b494c1320e5aacd7915b74d
Autor:
Cagri Toraman, Furkan Şahinuç
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030722395
ECIR (2)
ECIR (2)
Microblogs are characterized as short and informal text; and therefore sparse and noisy. To understand topic semantics of short text, supervised and unsupervised methods are investigated, including traditional bag-of-words and deep learning-based mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f998f813a4d60070d06edf6478703511
https://doi.org/10.1007/978-3-030-72240-1_50
https://doi.org/10.1007/978-3-030-72240-1_50
Publikováno v:
SIU
The rapid development of systems with artificial intelligence plays significant role in human-machine interaction. The artificial intelligence algorithms that take instructions via natural language, can provide appropriate answers to the commands the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8f6e210d0bd9ae9d3285a28d8f661402
https://doi.org/10.1109/siu49456.2020.9302308
https://doi.org/10.1109/siu49456.2020.9302308
Publikováno v:
Natural Language Engineering
As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words but the vectors corresp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79d3b21c7ae44d82bbf1b030c5e5569b
https://hdl.handle.net/11693/75864
https://hdl.handle.net/11693/75864
Autor:
Aykut Koc, Furkan Şahinuç
Publikováno v:
Information_Processing_&_Management
Being one of the most common empirical regularities, the Zipf’s law for word frequencies is a power law relation between word frequencies and frequency ranks of words. We quantitatively study semantic uncertainty of words through non-point distribu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ab589659e3c339b0b68739d47840ef6
https://doi.org/10.1016/j.ipm.2021.102493
https://doi.org/10.1016/j.ipm.2021.102493