search

jiesutd / LatticeLSTM

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.
1.8k stars 453 forks source link

读取gigaword_chn.all.a2b.bi.ite50.vec文件出错 #1

Closed Robets2020 closed 6 years ago

Robets2020 commented 6 years ago

下面这两的向量维度不是50，一个是15，一个是 55， 是这个文件本来的问题，还是我下载过程中传输出错了（没有百度网盘会员，下的真慢）？

森悄 -0.420138 -0.189634 0.346326 -0.235297 -0.389551 -0.588 1.164976 -0.610863 0.073047 0.531165 -3.343037 -0.666090 2.384061 0.129748 -1.972636

系v 0.108717 -0.042028 -2.452340 -0.387857 1.953125 0.230040 2.203831 3.083842 0.400699 -0.449208 1.321026 -2.430978 1.369693 0.100625 -1.246027 -0.846308 -2.649471 0.168484 0.593922 -0.481574 0.546810 -2.844704 -0.956998 -2.017416 1.072134 -1.407300 -0.145390 -0.086188 -0.896394 2.064528 1.660699 0.500353 0.773185 -2.036687 3.072354 0.667415 -0.520374 -1.668948 0.729110 0.385540 -0.868025 0.600913 1.883432 3.111219 -1.039192 1.274076 1.103154 3.524141 -0.77819 -2.084318 -1.281501 -2.526086 -2.124930 -0.793325 -0.496073

jiesutd commented 6 years ago

This may be caused by the network problem. Bigram embeddings are not necessary for lattice LSTM, you can check the readme file carefully, only unigram embeddings .uni. and Word Embeddings ctb.* are needed.

Robets2020 commented 6 years ago

Thank you. I am reading the source code and also surprised why this file is needed. In source code gaz_file = None so that ctb.* is not needed.

jiesutd commented 6 years ago

Oh, if you want to set gaz_file=None, then it is the baseline without lattice. You should set the gaz_file=ctb.* to build the lattice lstm.

Robets2020 commented 6 years ago

Thank you. I should read experiments of the paper again.