Yijia Liu

Fix: TypeError: __repr__() takes at most 3 arguments (4 given)

1

Dear Dr. Tse, I put a sentence `( (IP (LCP (NP (ADJP (JJ 下列)) (NP (NN 句子))) (LC 中)) (PU ，) (QP (CP (IP (VP (VE 没有) (NP (NN 病句))))...

fix issue #5

2

igraph -> python-igraph

词性标注实验

7

用这个issue记录实验过程。 - [ ] 模型1 - [ ] 模型2 - [ ] 模型3

词性标注实验提高性能的方案

6

- [x] 1. 增加迭代轮次 [无效] - [ ] 2. 设计一些特征，具体可以参考c&w 2011 - [ ] 3. seqlabeling中加入tag信息，现在的模型没有考虑tag转移，如果能把前一个tag也作为输入输进去，对于预测当前tag应该比较有用 - [ ] 4. 用crf - [ ] 5. 将数字时间进行normalize

Hi Jeff, According to https://github.com/jflanigan/jamr/blob/Semeval-2016/docs/Hand_Alignments.md, hand alignment is annotated for LDC2013E117. We would like to work on the alignment problem but we don't have access to the LDC2013E117 data. But...

* [x] alignment for LDC2017T10 * [ ] CCG-AMR alignment hack * [ ] amr-eager alignment hack * [ ] CacheTransition-Seq2Seq alignment hack

code for seq-level distillation

1

Hi Yoon, As mentioned in the [Sequence-Level Knowledge Distillation](https://arxiv.org/pdf/1606.07947.pdf), implementation of the distillation model is released in this repo, but I didn't find the corresponding code (both word-level distillation and...