whuir / me-cner Goto Github PK
View Code? Open in Web Editor NEWCode for CIKM 2019 paper "Exploiting Multiple Embeddings for Chinese Named Entity Recognition".
Code for CIKM 2019 paper "Exploiting Multiple Embeddings for Chinese Named Entity Recognition".
for predict_label, gt_label in zip(predict, ground_truth):
print('debug', predict_label, gt_label)
if predict_label in [1, 3, 5, 7]: # B-XXX
precision_denominator += 1
pred_category = (predict_label + 1) // 2 # 0-NIL, 1-ORG, 2-LOC, 3-PER, 4-GPE, 5-O
gt_category = (gt_label + 1) // 2
confusion_matrix[pred_category][gt_category] += 1
if gt_label in [1, 3, 5, 7]: # B-XXX
recall_denominator += 1
pred_category = (predict_label + 1) // 2 # 0-NIL, 1-ORG, 2-LOC, 3-PER, 4-GPE, 5-O
gt_category = (gt_label + 1) // 2
confusion_matrix[pred_category][gt_category] += 1
# O, NIL or B-XXX, means the previous NER complete
if gt_label in [0, 1, 3, 5, 7, 9] and \
predict_label in [0, 1, 3, 5, 7, 9] and (
match_candidate[0] > 0 or match_candidate[1] > 0):
match_candidate = (0, 0)
numerator += 1
if predict_label == gt_label and predict_label not in [0, 9]:
match_candidate = (predict_label, gt_label)
if predict_label != gt_label:
match_candidate = (0, 0)
这里好像只用了B标签去计算F1得分,还是我理解有问题?
作者大大您好,我用腾讯词向量Large版本得到的结果也很低,原论文P R F1 :75.17 64.39 68.93 我的结果 64.63 52.22 57.77,,请作者大大赐教一下,,还有可能是哪里的问题,这对我非常重要啊
我用提供的数据按照demo跑了一下,在微博数据集上F1 score只有58.4,有什么需要注意的吗?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.