ir_datasets
: TREC Robust 2004The TREC Robust retrieval task focuses on "improving the consistency of retrieval technology by focusing on poorly performing topics."
The TREC Robust document collection is from TREC disks 4 and 5. Due to the copyrighted nature of the documents, this collection is for research use only, which requires agreements to be filed with NIST. See details here.
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>
Robust04 Fold 1 (Title) proposed by Huston & Croft (2014) and used in numerious works
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold1')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold1')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold1')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>
Robust04 Fold 2 (Title) proposed by Huston & Croft (2014) and used in numerious works
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold2')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold2')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold2')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>
Robust04 Fold 3 (Title) proposed by Huston & Croft (2014) and used in numerious works
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold3')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold3')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold3')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>
Robust04 Fold 4 (Title) proposed by Huston & Croft (2014) and used in numerious works
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold4')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold4')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold4')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>
Robust04 Fold 5 (Title) proposed by Huston & Croft (2014) and used in numerious works
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold5')
for query in dataset.queries_iter():
query # namedtuple<query_id, title, description, narrative>
Language: en
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold5')
for doc in dataset.docs_iter():
doc # namedtuple<doc_id, text, marked_up_doc>
Relevance levels
Rel. | Definition |
---|---|
0 | not relevant |
1 | relevant |
2 | highly relevant |
Example
import ir_datasets
dataset = ir_datasets.load('trec-robust04/fold5')
for qrel in dataset.qrels_iter():
qrel # namedtuple<query_id, doc_id, relevance, iteration>