@jdongca2003, hope you are doing fine.
I was reading your research paper entitled 'Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus' which generates word embedding vectors based on an algorithm that concatenates 300-dimentional pretrained GLOVE embeddings and 100-dimentional word-2-vec embeddings estimated on UDC. But as a matter of fact I am unable to locate this algorithm in the source code.
Could you please provide me the source code of the algorithm that generates the 'glove_42B_300d_vec_plus_word2vec_100.txt' file used in the Ubuntu_train.sh script ?
I would be really thankful for this.
@jdongca2003, hope you are doing fine.
I was reading your research paper entitled 'Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus' which generates word embedding vectors based on an algorithm that concatenates 300-dimentional pretrained GLOVE embeddings and 100-dimentional word-2-vec embeddings estimated on UDC. But as a matter of fact I am unable to locate this algorithm in the source code.
Could you please provide me the source code of the algorithm that generates the 'glove_42B_300d_vec_plus_word2vec_100.txt' file used in the Ubuntu_train.sh script ?
I would be really thankful for this.