Accomplishments
Our paper is done and we have sat down to discuss our summer plans. We plan to investigate a recurrent Neural Network structure instead of a Convolutional one. We also plan to investigate new metric ideas instead of focusing only on the standard metric. All of these ideas came from attending confrences and talking to people, so I thank all of them for their input!
Weekly goal
Study and succeed in our finals.
Automatic Tagging of Stack Overflow Questions Using Global Vectors and Deep Learning
Tuesday, April 30, 2019
Tuesday, April 23, 2019
Week 28
Accomplishments
Our final paper is well on its way to completeness. We have everything transferred over from our other papers now we are just finishing odds and ends and struggling with ensuring our citations are correctly logged in Zotoro.
Here is an exert of our paper~
Question-and-answer (Q&A) websites like Stack Overflow require users to attach up to five tags when they submit a question. However, users may assign tags that are not relevant to the question. A better approach would be to recommend to users the most appropriate tags for their question and let them choose. The goal of this project is to combine newly developed natural language representations together with deep learning algorithms to improve the prediction accuracy of tags for Stack Overflow questions. We used word representations generated by word2vec and a Convolutional Neural Network.
Weekly Goal
Finish the paper!
Our final paper is well on its way to completeness. We have everything transferred over from our other papers now we are just finishing odds and ends and struggling with ensuring our citations are correctly logged in Zotoro.
Here is an exert of our paper~
Question-and-answer (Q&A) websites like Stack Overflow require users to attach up to five tags when they submit a question. However, users may assign tags that are not relevant to the question. A better approach would be to recommend to users the most appropriate tags for their question and let them choose. The goal of this project is to combine newly developed natural language representations together with deep learning algorithms to improve the prediction accuracy of tags for Stack Overflow questions. We used word representations generated by word2vec and a Convolutional Neural Network.
Weekly Goal
Finish the paper!
Tuesday, April 16, 2019
Week 27
Accomplishments
The STEM Showcase went well. We had a lot of young students come up to talk to us about our research, so hopefully we inspired some young programmers. We also sat down and started discuusing what will be needed in our final report.
Weekly Goal
Look through the papers we have written to submit to conferences and expand where needed for the final paper.
The STEM Showcase went well. We had a lot of young students come up to talk to us about our research, so hopefully we inspired some young programmers. We also sat down and started discuusing what will be needed in our final report.
Weekly Goal
Look through the papers we have written to submit to conferences and expand where needed for the final paper.
Tuesday, April 9, 2019
Week 26
Accomplishments
We presented at COFSP and were the second place team for our set of judges. We had a tough time presenting as one of our judges specialized in Natural Language processing and Deep learning and our other judge did not even know what Machine Learning is. We were given some great advice by the knowledgeable judge that we plan to implement during our summer extension.
Weekly Goal
We have one more day of presenting at our school's STEM Showcase.
We presented at COFSP and were the second place team for our set of judges. We had a tough time presenting as one of our judges specialized in Natural Language processing and Deep learning and our other judge did not even know what Machine Learning is. We were given some great advice by the knowledgeable judge that we plan to implement during our summer extension.
Weekly Goal
We have one more day of presenting at our school's STEM Showcase.
Tuesday, April 2, 2019
Week 25
Accomplishments
This week was QUEST, a research competition at our university. We participated and presented to 2 judges, using all that we learned from our first conference. We were able to give informed presentations that had the judges asking us deep questions about our model.\
Weekly Goal
The COFSP conference is this weekend, so staying prepared to present. Also, including fasttext into our analysis.
This week was QUEST, a research competition at our university. We participated and presented to 2 judges, using all that we learned from our first conference. We were able to give informed presentations that had the judges asking us deep questions about our model.\
Weekly Goal
The COFSP conference is this weekend, so staying prepared to present. Also, including fasttext into our analysis.
Subscribe to:
Posts (Atom)