Loading...
Please wait, while we are loading the content...
Similar Documents
Sentence Similarity Prediction based on Siamese CNN-Bidirectional LSTM with Self-attention
| Content Provider | Semantic Scholar |
|---|---|
| Author | Kim, Mintae Oh, Yeongtaek Kim, Wooju |
| Copyright Year | 2019 |
| Abstract | A deep learning model for semantic similarity between sentences was presented. In general, most of the models for measuring similarity word use level or morpheme level embedding. However, the attempt to apply either word use or morpheme level embedding results in higher complexity of the model due to the large size of the dictionary. To solve this problem, a Siamese CNN-Bidirectional LSTM model that utilizes phonemes instead of words or morphemes and combines long short term memory (LSTM) with 1D convolution neural networks with various window lengths that bind phonemes is proposed. For evaluation, we compared our model with Manhattan LSTM (MaLSTM) which shows good performance in measuring similarity between similar questions in the Naver Q&A dataset (similar to Kaggle Quora Question Pair). |
| Starting Page | 241 |
| Ending Page | 245 |
| Page Count | 5 |
| File Format | PDF HTM / HTML |
| DOI | 10.5626/jok.2019.46.3.241 |
| Volume Number | 46 |
| Alternate Webpage(s) | http://kiise.or.kr/e_journal/2019/3/JOK/pdf/04.pdf |
| Alternate Webpage(s) | https://doi.org/10.5626/jok.2019.46.3.241 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
