18105197. TRANSLITERATED SEARCH METHOD AND ELECTRONIC DEVICE SUPPORTING SAME simplified abstract (Samsung Electronics Co., Ltd.)
TRANSLITERATED SEARCH METHOD AND ELECTRONIC DEVICE SUPPORTING SAME
Organization Name
Inventor(s)
Balabhaskar Veerannagari of Bengaluru (IN)
Hemant Tiwari of Bengaluru (IN)
Mukund Rungta of Bengaluru (IN)
Surendra Kumar Kanisetty of Bengaluru (IN)
TRANSLITERATED SEARCH METHOD AND ELECTRONIC DEVICE SUPPORTING SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18105197 titled 'TRANSLITERATED SEARCH METHOD AND ELECTRONIC DEVICE SUPPORTING SAME
Simplified Explanation
The abstract describes an electronic device that includes a processor and memory to store a dictionary and index information. The device can perform various tasks related to transliteration and language translation using machine learning.
- The device can extract text in a first language from data and check if there is a transliteration pair in the dictionary.
- If a transliteration pair is found, the device indexes the first text and at least one second text to the data and stores this information in the index.
- If no transliteration pair is found, the device uses a machine learning model to transliterate the first text into a second language and extracts the transliterated text.
- The device then indexes the first text and the extracted transliterated text to the data and stores this information in the index.
Potential Applications
- Language translation and transliteration in electronic devices.
- Improving the accuracy and efficiency of language translation processes.
- Enhancing the capabilities of language learning applications.
Problems Solved
- Difficulty in accurately transliterating text between different languages.
- Limited availability of transliteration pairs in existing dictionaries.
- Time-consuming and manual process of transliteration.
Benefits
- Improved accuracy and efficiency in transliteration and language translation.
- Expanded availability of transliteration pairs through machine learning.
- Automated and faster transliteration process.
Original Abstract Submitted
An electronic device includes a processor and a memory to store a dictionary and index information. The memory can store instructions to cause the processor to: extract a first text in a first language included in data; determine whether or not a transliteration pair is included in the dictionary; if the transliteration pair is identified, index the first text and at least one second text to the data and store same in the index information; and, if the transliteration pair is not identified, extract at least one third text in the second language by inputting the extracted first text to a machine learning model for transliterating an input in the first language into the second language and extracting same, and index the first text and the at least one third text which has been extracted to the data and store same in the index information.
- Samsung Electronics Co., Ltd.
- Jeongpyo Lee of Suwon-si (KR)
- Namgyu Kim of Suwon-si (KR)
- Balabhaskar Veerannagari of Bengaluru (IN)
- Hemant Tiwari of Bengaluru (IN)
- Mukund Rungta of Bengaluru (IN)
- Surendra Kumar Kanisetty of Bengaluru (IN)
- Vanraj Vala of Bengaluru (IN)
- Jungmin Park of Suwon-si (KR)
- G06F40/58
- G06F40/242
- G06F40/284
- G06F16/33
- G06N3/045
- G06N3/08