Hello,
I am Tanmoy Ghosh, a B.Tech final year student at National Institute of
Technology Durgapur, India majoring in Computer Science and Engineering. I
am primarily interested in the experimental areas of *Natural Language
Processing* and *Machine Learning* as well as coding and am well versed in
Python and the libraries related to Natural Language Processing and Machine
Learning (e.g. numpy, pandas, nltk, scikit-learn, TensorFlow, Keras, etc).
I possess a good grasp of the recent trends in NLP and have research
experience in it. I have worked at *Ubiquitous Knowledge Processing Lab *at* TU
Darmstadt *under the guidance of Dr Iryna Gurevych as a part of *DAAD WISE
programme*.
I went through the GSoC project ideas of DBpedia and the topic "*DBpedia
Live Neural Question Answering Chatbot*" fascinated me. I read the
paper "*SPARQL
as a foreign language*" and did the warmup tasks mentioned like forking the
NSpM project and training with the monument datasets. I have also
instantiated the *NSpM-telegram-bot.*
But I have a query related to the task -
(4)Fork and train the model using a subset (30 first lines) of DBNQA
dataset
Since there are multiple topics (art, personal, other, sports) which
particular CSV file should I use to train the model?
Thanks and regards,
Tanmoy Ghosh
_______________________________________________
Dbpedia-gsoc mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc
