We introduce a novel mixed characterword architecture to improve Chinese sentence representations, by utilizing rich semantic information of word internal structures. Our architecture uses two key strategies. The first is a mask gate on characters, learning the relation among characters in a word. The second is a maxpooling operation on words, adaptively finding the optimal mixture of the atomi...

This paper makes an attempt to segment the handwritten Hindi words. The problem of segmentation is compounded by the possible presence of modifiers (matras) on all sides of the basic characters and due to the uncertainty introduced in the character shapes by way of different writing styles. We have devised a structural approach to capture the similarities and differences between structure class...

This paper describes an interpretation system for on-line cursive handwriting that requires very little initial training and that rapidly learns, and thus adapts to, the handwriting style of a user. Key features are a shape analysis algorithm that eeciently determines shapes in the handwritten word, a linear segmentation algorithm that optimally matches characters identiied in the handwritten w...

This paper presents a system that is being developed for the recognition of the handwritten legal amount in Brazilian bank checks. Our strategy used to approach the handwritten legal amount recognition problem puts on evidence the key-words: "mil", "reais/real", "centavos/centavo" which are almost always present in each amount. The recognizer, based on Hidden Markov Models, does a global word a...

Machine transliteration is an automatic method to generate characters or words in one alphabetical system for the corresponding characters in another alphabetical system. Machine transliteration can play an important role in natural language application such as information retrieval and machine translation, especially for handling proper nouns and technical terms. The previous works focus on ei...

Analyses of living and fossil taxa are crucial for understanding biodiversity through time. The total evidence method allows living and fossil taxa to be combined in phylogenies, using molecular data for living taxa and morphological data for living and fossil taxa. With this method, substantial overlap of coded anatomical characters among living and fossil taxa is vital for accurately inferrin...

To show that, in reading, a fundamental and unconscious perceptual process occurs beyond the current fixation, we examined whether peripherally presented characters of Chinese words in such extreme viewing conditions could be grouped when some characters were rendered invisible while others were visible. We presented a pair of two-character Chinese words and indexed whether the visible and invi...

– 212 words Total characters – 23,636 characters (including spaces)