search

lanwuwei / SPM_toolkit

Neural network toolkit for sentence pair modeling.
303 stars 70 forks source link

Do you use pre-trained word embedding when training infer-sent model on Quora Dataset? #12

Closed mapingshuo closed 6 years ago

mapingshuo commented 6 years ago

Hi, I am trying to reproduce your result in the paper: "Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering", where you got 86.6% test acc on Quora dataset with the inferSent model. I wonder whether you use Pre-trained word embedding or not, because the facebook group use Pre-trained word embedding in their paper: "Supervised Learning of Universal Sentence Representations from Natural Language Inference Data". Thanks.

lanwuwei commented 6 years ago

Yes, I used pre-trained GloVe word vectors: GLOVE_PATH = basepath + "/pytorch/DeepPairWiseWord/VDPWI-NN-Torch/data/glove/glove.840B.300d.txt"

mapingshuo commented 6 years ago

Thanks for your reply, it's so helpful!