用户工具

站点工具


zh:notes:math_softwares

差别

这里会显示出您选择的修订版和当前版本之间的差别。

到此差别页面的链接

两侧同时换到之前的修订记录 前一修订版
后一修订版
前一修订版
zh:notes:math_softwares [2026/08/23 17:57]
pzczxs [Export for Gaussian AT credit Model]
zh:notes:math_softwares [2026/08/24 10:15] (当前版本)
pzczxs [Obtain Embedding from a Vector Model]
行 36: 行 36:
  
 ==== Obtain Embedding from a Vector Model ==== ==== Obtain Embedding from a Vector Model ====
 +The //​text-embedding-v4//​ model is employed to produce a 64-demensional embedding vector for each word. 
 <code bash> <code bash>
-> python .\extract_embedding.py --resume .\math_software.word.vocab+> python .\extract_embedding.py ​--model text-embedding-v4 --dimension 64 --batch-size 10 --output text-embedding-v4-64.txt ​--resume .\math_software.word.vocab
 </​code>​ </​code>​
 ==== Count One- and Two- Grams for PMI Calculation ==== ==== Count One- and Two- Grams for PMI Calculation ====
行 87: 行 88:
 Project: <color red>​GaussianATModelWithCredit</​color>​ Project: <color red>​GaussianATModelWithCredit</​color>​
  
 +==== GloVe Embedding ====
 <code bash> <code bash>
 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​10/​math_software -K 10 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​10/​math_software -K 10
行 98: 行 100:
 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​90/​math_software -K 90 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​90/​math_software -K 90
 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​100/​math_software -K 100 > java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 50 -e resources/​glove.2024.wikigiga.50d.zip -n 50 -sc 7 -fb data/​math_software/​100/​math_software -K 100
 +</​code>​
 +
 +==== text-embedding-v4 ====
 +<code bash>
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​10/​math_software -K 10
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​20/​math_software -K 20
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​30/​math_software -K 30
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​40/​math_software -K 40
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​50/​math_software -K 50
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​60/​math_software -K 60
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​70/​math_software -K 70
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​80/​math_software -K 80
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​90/​math_software -K 90
 +> java -Xmx20g -jar GaussianATCreditModel.jar -sf -D 256 -e resources/​qwen3.7-embeddings.zip -n 50 -sc 7 -fb data/​math_software/​100/​math_software -K 100
 </​code>​ </​code>​
 ===== Calculate Diversity Indicators ===== ===== Calculate Diversity Indicators =====
 The following three diversity indicators are calculated: (1) Rao-Stirling ([[https://​www.jstor.org/​stable/​25050293|Rao,​ 1982]]; [[https://​doi.org/​10.1098/​rsif.2007.0213|Stirling,​ 2007]]), DIV ([[https://​doi.org/​10.1016/​j.joi.2019.03.016|Leydesdorff et al., 2019]]), and Diversity ([[https://​doi.org/​10.1007/​s11192-022-04336-3|Mutz,​ 2022]]). ​ The following three diversity indicators are calculated: (1) Rao-Stirling ([[https://​www.jstor.org/​stable/​25050293|Rao,​ 1982]]; [[https://​doi.org/​10.1098/​rsif.2007.0213|Stirling,​ 2007]]), DIV ([[https://​doi.org/​10.1016/​j.joi.2019.03.016|Leydesdorff et al., 2019]]), and Diversity ([[https://​doi.org/​10.1007/​s11192-022-04336-3|Mutz,​ 2022]]). ​
zh/notes/math_softwares.1787479057.txt.gz · 最后更改: 2026/08/23 17:57 由 pzczxs