search

thunlp / NRE

Neural Relation Extraction, including CNN, PCNN, CNN+ATT, PCNN+ATT
MIT License
810 stars 309 forks source link

Word embeddings file #24

Open aniket-sen opened 6 years ago

aniket-sen commented 6 years ago

Would you like to share how the word embedding file was created, like what procedure was used. And also if I want this algorithm to work on my dataset, how am I supposed to create a word embedding file for my dataset

Mrlyk423 commented 6 years ago

See the ReadMe. Pre-Trained Word Vectors are learned from New York Times Annotated Corpus (LDC Data LDC2008T19), which should be obtained from LDC (https://catalog.ldc.upenn.edu/LDC2008T19). And we also provide the word embedding file 'vec.bin' used in the experiments in data.zip.

aniket-sen commented 6 years ago

You didn't answer my last question

ghost commented 6 years ago

You can use gensim to train vector on your own dataset