search

IDEA-FinAI / ToG

This is the official github repo of Think-on-Graph. If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email (xuchengjin@idea.edu.cn)
391 stars 43 forks source link

Question about the datasets #30

Closed Icamd closed 2 months ago

Icamd commented 3 months ago

Hi! Thank you for your work!

I ran the test example without installing the Freebase dataset and encountered an error at "results = sparql.query().convert()", which says: "{URLError} <urlopen error [Errno 111] Connection refused". When I run main_freebase.py, it also reports "urllib.error.URLError: <urlopen error [Errno 110] Connection timed out". Can this issue be resolved by installing the Freebase dataset, or is it caused by an internet connection error? Thank you!

Additionally, is it possible to avoid installing the dataset? My server doesn't have 400GB of RAM, making it very difficult for me to run the program. Projects like RoG (Reasoning on Graph) can run on WebQSP and CWQ with only a few hundred MBs of memory. Is it possible to run ToG with a single dataset (like WebQSP) with less memory consumption? Thank you!

GasolSun36 commented 3 months ago

Hi! Thank you for your work!

I ran the test example without installing the Freebase dataset and encountered an error at "results = sparql.query().convert()", which says: "{URLError} <urlopen error [Errno 111] Connection refused". When I run main_freebase.py, it also reports "urllib.error.URLError: <urlopen error [Errno 110] Connection timed out". Can this issue be resolved by installing the Freebase dataset, or is it caused by an internet connection error? Thank you!

Additionally, is it possible to avoid installing the dataset? My server doesn't have 400GB of RAM, making it very difficult for me to run the program. Projects like RoG (Reasoning on Graph) can run on WebQSP and CWQ with only a few hundred MBs of memory. Is it possible to run ToG with a single dataset (like WebQSP) with less memory consumption? Thank you!

You can refer to this issue: https://github.com/GasolSun36/ToG/issues/20

Icamd commented 2 months ago

Hi! Thank you for your work! I ran the test example without installing the Freebase dataset and encountered an error at "results = sparql.query().convert()", which says: "{URLError} <urlopen error [Errno 111] Connection refused". When I run main_freebase.py, it also reports "urllib.error.URLError: <urlopen error [Errno 110] Connection timed out". Can this issue be resolved by installing the Freebase dataset, or is it caused by an internet connection error? Thank you! Additionally, is it possible to avoid installing the dataset? My server doesn't have 400GB of RAM, making it very difficult for me to run the program. Projects like RoG (Reasoning on Graph) can run on WebQSP and CWQ with only a few hundred MBs of memory. Is it possible to run ToG with a single dataset (like WebQSP) with less memory consumption? Thank you!

You can refer to this issue: GasolSun36/ToG#20

Thank you! I have another question. In some dataset samples (like WebQSP), the answer entity is not included in the graph and cannot be extracted using the normal ToG process. However, CoT appears to have the knowledge to answer the question and provides the correct answer even when it is not present in the graph. How is the Hits@1 value calculated in this situation? Does it mean that even if the answer entity is not included in the graph, if CoT answers it correctly, the Hits@1 is still considered as 1? Also, is this computation process reported in the paper? Thank you!