Knowledge Base Embeddings for DBpedia. Hello folks, This is my final blog post for GSoC 2017, which is a 3 month long programme hosted by Google, where selected students all over the world participate in the summers on projects for various open source organizations. I was participating for the organization DBpedia. I would be summarizing … Continue reading GSoC 2017 Final Submission
Hello folks, Last week, I ran DBpedia Code using the existing hyperparameters which were tuned for Freebase dataset. So, the hyper parameters had to properly tuned for the DBpedia subsets, and then compared based on the evaluations. After discussing with the mentors, we decided that we would take 3 sizes of the different DBpedia subsets. … Continue reading Week 9 & 10 : Hyper-parameter tuning on various DBpedia subsets
Hello folks, This week I created 4 sets from Freebase mapped DBpedia dataset: 1) SET 0 : All DBpedia mapped dataset (with all the predicates including : type, subject, wikilinks, assame as predicates; and literals objects)) : On running the code, I found that the codes do NOT run with literals kind of data. So, … Continue reading Week 8 : Experimenting with different DBpedia sets
Hello folks, This week I used Freebase mapped DBpedia dataset for training the models. There were a few challenges which came along the way. If you check my blog for Week 5, you would realize that for each triple of Freebase dataset, I found the subject, and for that subject I extracted all the DBpedia … Continue reading Week 6 : Executing code on a DBpedia subset
Hello folks, This week I wrote a code FreebaseToDBpedia.py to make a dataset with entities mapped from Freebase dataset.
Hello folks, This week is the final week before First Evaluation between 26th June to 30th June. So I took all the experiment results together and do some analysis for taking the next steps. Earlier I had noted MRR and Hits@10 metric only. But I decided to expand the table to consider Hits@1 and Hits@3 … Continue reading Week 4 : Assembling all the pieces before First Evaluation
Hello folks, In Weeks 2 and 3, I explored two other approaches : DistMult and SSP. The code for DistMult executed successfully. However the code for SSP could not be executed successfully. The SSP code was originally built in Windows OS on Visual Studio using Intel C++ compiler. I and my mentor Sandro tried to … Continue reading Week 2 and 3 : Exploration !