Deep learning Chinese input method with incremental vocabulary selection
The core task of an input method is to convert the keystroke sequences typed by users into Chinese character sequences.Input methods applying deep learning methods have advantages in learning long-range dependencies and solving data sparsity problems.However, the existing methods still have two shor...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2022-12-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022294/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530731201822720 |
|---|---|
| author | Huajian REN Xiulan HAO Wenjing XU |
| author_facet | Huajian REN Xiulan HAO Wenjing XU |
| author_sort | Huajian REN |
| collection | DOAJ |
| description | The core task of an input method is to convert the keystroke sequences typed by users into Chinese character sequences.Input methods applying deep learning methods have advantages in learning long-range dependencies and solving data sparsity problems.However, the existing methods still have two shortcomings: the separation structure of pinyin slicing in conversion leads to error propagation, and the model is complicated to meet the demand for real-time performance of the input method.A deep-learning input method model incorporating incremental word selection methods was proposed to address these shortcomings.Various softmax optimization methods were compared.Experiments on People’s Daily data and Chinese Wikipedia data show that the model improves the conversion accuracy by 15% compared with the current state-of-the-art model, and the incremental vocabulary selection method makes the model 130 times faster without losing conversion accuracy. |
| format | Article |
| id | doaj-art-2bfc64033ab242fb828af8bb47c405a6 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2022-12-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-2bfc64033ab242fb828af8bb47c405a62025-01-15T02:59:45ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012022-12-0138566459574298Deep learning Chinese input method with incremental vocabulary selectionHuajian RENXiulan HAOWenjing XUThe core task of an input method is to convert the keystroke sequences typed by users into Chinese character sequences.Input methods applying deep learning methods have advantages in learning long-range dependencies and solving data sparsity problems.However, the existing methods still have two shortcomings: the separation structure of pinyin slicing in conversion leads to error propagation, and the model is complicated to meet the demand for real-time performance of the input method.A deep-learning input method model incorporating incremental word selection methods was proposed to address these shortcomings.Various softmax optimization methods were compared.Experiments on People’s Daily data and Chinese Wikipedia data show that the model improves the conversion accuracy by 15% compared with the current state-of-the-art model, and the incremental vocabulary selection method makes the model 130 times faster without losing conversion accuracy.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022294/Chinese input methodlong short-term memoryvocabulary selection |
| spellingShingle | Huajian REN Xiulan HAO Wenjing XU Deep learning Chinese input method with incremental vocabulary selection Dianxin kexue Chinese input method long short-term memory vocabulary selection |
| title | Deep learning Chinese input method with incremental vocabulary selection |
| title_full | Deep learning Chinese input method with incremental vocabulary selection |
| title_fullStr | Deep learning Chinese input method with incremental vocabulary selection |
| title_full_unstemmed | Deep learning Chinese input method with incremental vocabulary selection |
| title_short | Deep learning Chinese input method with incremental vocabulary selection |
| title_sort | deep learning chinese input method with incremental vocabulary selection |
| topic | Chinese input method long short-term memory vocabulary selection |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022294/ |
| work_keys_str_mv | AT huajianren deeplearningchineseinputmethodwithincrementalvocabularyselection AT xiulanhao deeplearningchineseinputmethodwithincrementalvocabularyselection AT wenjingxu deeplearningchineseinputmethodwithincrementalvocabularyselection |