Xinyu Wang
Xinyu Wang
In my environment (pytorch 0.4.0), it will report error for line 78: word = itow[str(ix)] Because ix is a tensor, so it is better to use ix.item() to replace the...
Hi, I'm very instersted in your great work. For simpler running the code, are there any conversion script that convert the `.conll` file to `.jsonlines` files? Thank you!
Hi, I'm trying to extract bert features by `extract_bert_features.sh`. I find that the token features are extracted based on a document-level, which generates embeddings based on a sequence of sentences,...
Thank you for your released codes. I tried to follow your instruction to train the model but I cannot reproduce your reported results in the paper. The F1 score on...
Hi, In the paper, the Twitter 2017 datasets contain 3373/723/723 sentences for train/dev/test respectively. However, in the paper of [Lu et al., 2018](https://www.aclweb.org/anthology/P18-1185/), they reported that there are 4290/1432/1459 sentences...
Hi, I found that if I input `log_potential` into the `DependencyCRF` with some large values, the marginal distribution will be slightly over 1, and this also results in the `log_prob...