Train the Siamese LSTM network to detect similarity between two sentences(Python)
Budget: $30 – $250 USD
Train the model with two different approach to detect either the two sentence are semantically different or not.(Plagiarism detection)
Dataset in Urdu Language. Total pair of sentence in training dataset will be 5400.
Corpus contain three column (Sentence1,Sentence2,Similarity)
Following are the two models.
1- Siamese Manhattan LSTM
2-Siamese Deep Neural Network based on LSTM.
Links for your better understanding:
1-https://blog.mlreview.com/implementing-malstm-on-kaggles-quora-question-pairs-
competition-8b31b0b16a07
2-https://freesoft.dev/program/126476792
Dataset in Urdu Language. Total pair of sentence in training dataset will be 5400.
Corpus contain three column (Sentence1,Sentence2,Similarity)
Following are the two models.
1- Siamese Manhattan LSTM
2-Siamese Deep Neural Network based on LSTM.
Links for your better understanding:
1-https://blog.mlreview.com/implementing-malstm-on-kaggles-quora-question-pairs-
competition-8b31b0b16a07
2-https://freesoft.dev/program/126476792