Open msharara1998 opened 10 months ago
Hi, you can find a very condensed example here.
queries
is a list of dictionaries where each dictionary has two keys: q_id
and text
.
Both q_id
and text
must be strings.
qrels
is a dictionary of dictionaries.
The parent dictionary keys must be the q_id
of the dictionaries in the queries
list.
Each child dictionary has a key for each document relevant to the corresponding query.
The values corresponding to the keys are the relevance score judgments (i.e., how well the document answer the query). Note that they can be both graded or binary (zero means not relevant). Most metrics for performance evaluation of search engines consider all non-judged documents as non-relevants. Therefore, you are good by providing scores only for the documents you know are relevant.
Example of qrels
:
qrels = { "q_1": { "d_12": 5, "d_25": 3 },
"q_2": { "d_11": 6, "d_22": 1 } }
Let me know if it is clear. :)
I am looking for an example of how to structure the
queries
andqrels
parameters of the autotune function because I searched in the repo and didn't find any example for that. Precisely, what should be the keys and values ofqueries
dict? and similarly forqrels
dict?Thanks in advance for your help.