Search

Your search keyword '"Ryu, Pum-Mo"' showing total 8 results
Start Over Author "Ryu, Pum-Mo" Language english
8 results on '"Ryu, Pum-Mo"'

7. An Empirical Research on Extracting Relations from Wikipedia Text.

Author

Huang, Jin-Xia, Ryu, Pum-Mo, and Choi, Key-Sun

Abstract

A feature based relation classification approach is presented, in which probabilistic and semantic relatedness features between patterns and relation types are employed with other linguistic information. The importance of each feature set is evaluated with Chi-square estimator, and the experiments show that, the relatedness features have big impact on the relation classification performance. A series experiments are also performed to evaluate the different machine learning approaches on relation classification, among which Bayesian outperformed other approaches including Support Vector Machine (SVM). [ABSTRACT FROM AUTHOR]

Published
2008
Full Text
View/download PDF

8. Improving code-switched ASR with linguistic information

Author

Chi, Jie, Bell, Peter, Calzolari, Nicoletta, Huang, Chu-Ren, Kim, Hansaem, Pustejovsky, James, Wanner, Leo, Choi, Key-Sun, Ryu, Pum-Mo, Chen, Hsin-Hsi, Donatelli, Lucia, Ji, Heng, Kurohashi, Sadao, Paggio, Patrizia, Xue, Nianwen, Kim, Seokhwan, Hahm, Younggyun, He, Zhong, Lee, Tony Kyungil, Santus, Enrico, Bond, Francis, and Na, Seung-Hoon

Abstract

This paper seeks to improve the performance of automatic speech recognition (ASR) systems operating on code-switched speech. Code-switching refers to the alternation of languages within a conversation, a phenomenon that is of increasing importance considering the rapid rise in the number of bilingual speakers in the world. It is particularly challenging for ASR owing to the relative scarcity of code-switching speech and text data, even when the individual languages are themselves well-resourced. This paper proposes to overcome this challenge by applying linguistic theories in order to generate more realistic code-switching text, necessary for language modelling in ASR. Working with English-Spanish code-switching, we find that Equivalence Constraint theory and part-of-speech labelling are particularly helpful for text generation, and bring 2% improvement to ASR performance.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results