Feature Space Augmentation for Negation Handling on Sentiment Analysis [PDF]
One crucial issue affecting the performance of sentiment analysis tasks is negation. Handling negation involves determining the negation scope and negation cue. Feature space augmentation is one approach used to address negation.
Ilmawan, Lutfi Budi+2 more
core +3 more sources
Authorship attribution in portuguese using character N-grams [PDF]
For the Authorship Attribution (AA) task, character n-grams are considered among the best predictive features. In the English language, it has also been shown that some types of character n-grams perform better than others. This paper tackles the AA task
Baptista, Jorge+2 more
core +1 more source
From secreit script to public print: punctuation, news management and the condemnation of the Earl of Bothwell [PDF]
The fall from power of James Hepburn, Earl of Bothwell, in 1567 was as dramatic as it was sudden. The survival of documents associated with the event gives us a rare insight into the ways in which texts were adapted for different purposes and readerships.
Smith, Jeremy J.
core +1 more source
Application of a MHD hybrid solar wind model with latitudinal dependences to Ulysses data at minimum [PDF]
In a previous work, Ulysses data was analyzed to build a complete axisymmetric MHD solution for the solar wind at minimum including rotation and the initial flaring of the solar wind in the low corona.
A. Aibéo+34 more
core +3 more sources
Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting. Most natural language processing applications expect segmented and well-formatted texts as input, which is not available in ASR
Kotlerman, Lili+5 more
core +1 more source
Codex Sinaiticus as a Window into Early Christian Worship [PDF]
Codex Sinaiticus is the oldest and most complete New Testament in Greek known to exist. Its two colophons at the end of 2 Esdras and Esther indicate a possible connection with Pamphilus’ famous library at Caesarea in Palestine.
Mitchell, Timothy N
core +2 more sources
Cognitive scale-free networks as a model for intermittency in human natural language
We model certain features of human language complexity by means of advanced concepts borrowed from statistical mechanics. Using a time series approach, the diffusion entropy method (DE), we compute the complexity of an Italian corpus of newspapers and ...
Allegrini, Paolo+2 more
core +3 more sources
Punctuating Old English Poetry: Challenges and Strategies [PDF]
As in other early language traditions, premodern English poetry was written out with very light punctuation. The sparsity of manuscript punctuation appears especially problematic in the period before 1200, when poetry in English lacked visual linebreaks.
Eric Weiskott
core +1 more source
Revised proposal to encode the Avestan script in the SMP of the UCS [PDF]
This is a proposal to encode the Avestan script in the international character encoding standard Unicode.
Everson, Michael, Pournader, Roozbeh
core
Interactive context-aware user-driven metadata correction in digital libraries [PDF]
Personal name variants are a common problem in digital libraries, reducing the precision of searches and complicating browsing-based interaction. The book-centric approach of name authority control has not scaled to match the growth and diversity of ...
Bainbridge, David+2 more
core +1 more source