Results 291 to 300 of about 191,232 (328)
Some of the next articles are maybe not open access.

Morphological cursive word segmentation

Proceedings 13th Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00878), 2002
The work describes a new algorithm for segmentation of handwritten cursive words, based on the following two hypotheses: 1) natural segmentation points (SPs) exist corresponding to disconnected characters; and 2) the physical SPs between connected characters are located in ligatures.
L.R. Veloso   +2 more
openaire   +1 more source

Word segmentation with universal prosodic cues

Cognitive Psychology, 2010
When listening to speech from one's native language, words seem to be well separated from one another, like beads on a string. When listening to a foreign language, in contrast, words seem almost impossible to extract, as if there was only one bead on the same string. This contrast reveals that there are language-specific cues to segmentation.
Ansgar D, Endress, Marc D, Hauser
openaire   +2 more sources

Incorporating Word Attention into Character-Based Word Segmentation

Proceedings of the 2019 Conference of the North, 2019
Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering. Typical segmentation models are categorized as character-based, for conducting exact inference, or word-based, for utilizing word-level information. We propose a character-based model utilizing
Shohei Higashiyama   +6 more
openaire   +1 more source

New Cyber Word Discovery Using Chinese Word Segmentation

2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 2019
Increasing new cyber words, if they could not be effectively identified, will seriously affect the accuracy of word segmentation, and bring great difficulties to the related work. In order to solve the problem that the Web text is not specific and the content is short, this paper proposes a new word discovery method combined with statistics and rules ...
Hao Wang   +3 more
openaire   +1 more source

Identifying coordinated compound words for Vietnamese word segmentation

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR), 2013
This paper proposes a dictionary-based method for determining coordinated compound words in Vietnamese. The main idea to determine whether two contiguous simple words in a text forms a coordinated compound word is based on their properties, part-of-speeches and the similarity between their definitions in the dictionary of the Vietnamese Computational ...
Ngoc Anh Tran   +2 more
openaire   +1 more source

Tibetan Word Segmentation Based on Word-Position Tagging

2013 International Conference on Asian Language Processing, 2013
The best advantage of Tibetan word segmentation based on word-position is to reduce segmentation errors for unknown words. In this article authors upgrade usual 4-tag set to 6-tag set to fit in with the features of Tibetan characters, using CRF as tagging model to train and test corpus data, then building post processing modules to revise the result ...
Caijun Kang, Di Jiang, Congjun Long
openaire   +1 more source

Beyond Word Segmentation

Current Directions in Psychological Science, 2013
The term statistical learning was originally used to describe sensitivity to conditional relations between syllables in the context of word segmentation. Subsequent research has demonstrated that infants are sensitive to many other kinds of statistical information.
Thiessen, Erik, Erickson, Lucy C.
openaire   +1 more source

Unsupervised word Segmentation Based on Word Influence

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Ruohao Yan   +3 more
openaire   +1 more source

Discriminative Word Alignment Over Multiple Word Segmentations

Chinese Journal of Electronics, 2014
Ning Xi   +3 more
openaire   +1 more source

Chinese Word Segmentation

2010
Kam-Fai Wong   +3 more
openaire   +1 more source

Home - About - Disclaimer - Privacy