← home
Github: datasets/trec_fair_2021.py

ir_datasets: TREC Fair Ranking 2021

Index
  1. trec-fair-2021
  2. trec-fair-2021/dev

"trec-fair-2021"

The TREC Fair Ranking track evaluates systems according to how well they fairly rank documents. The 2021 track focuses on fairly prioritising Wikimedia articles for editing to provide a fair exposure to articles from different groups.

docs

Language: en

Document type:
FairTrecDoc: (namedtuple)
  1. doc_id: str
  2. title: str
  3. text: str
  4. marked_up_text: str
  5. url: str
  6. quality_score: Union[float,None]
  7. geographic_locations: Union[List[str],None]
  8. quality_score_disk: Union[str,None]

Examples:

Python API 
import ir_datasets
dataset = ir_datasets.load("trec-fair-2021")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, title, text, marked_up_text, url, quality_score, geographic_locations, quality_score_disk>

You can find more details about the Python API here.

CLI 
ir_datasets export trec-fair-2021 docs
[doc_id]    [title]    [text]    [marked_up_text]    [url]    [quality_score]    [geographic_locations]    [quality_score_disk]
...

You can find more details about the CLI here.

PyTerrier 
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:trec-fair-2021')
# Index trec-fair-2021
indexer = pt.IterDictIndexer('./indices/trec-fair-2021')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['title', 'text', 'url'])

You can find more details about PyTerrier indexing here.

"trec-fair-2021/dev"

Official dev set.

queries

Language: en

Query type:
FairTrecQuery: (namedtuple)
  1. query_id: str
  2. text: str
  3. keywords: List[str]
  4. scope: str
  5. homepage: str

Examples:

Python API 
import ir_datasets
dataset = ir_datasets.load("trec-fair-2021/dev")
for query in dataset.queries_iter():
    query # namedtuple<query_id, text, keywords, scope, homepage>

You can find more details about the Python API here.

CLI 
ir_datasets export trec-fair-2021/dev queries
[query_id]    [text]    [keywords]    [scope]    [homepage]
...

You can find more details about the CLI here.

PyTerrier 
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:trec-fair-2021/dev')
index_ref = pt.IndexRef.of('./indices/trec-fair-2021') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pipeline(dataset.get_topics('text'))

You can find more details about PyTerrier retrieval here.

docs

Language: en

Note: Uses docs from trec-fair-2021

Document type:
FairTrecDoc: (namedtuple)
  1. doc_id: str
  2. title: str
  3. text: str
  4. marked_up_text: str
  5. url: str
  6. quality_score: Union[float,None]
  7. geographic_locations: Union[List[str],None]
  8. quality_score_disk: Union[str,None]

Examples:

Python API 
import ir_datasets
dataset = ir_datasets.load("trec-fair-2021/dev")
for doc in dataset.docs_iter():
    doc # namedtuple<doc_id, title, text, marked_up_text, url, quality_score, geographic_locations, quality_score_disk>

You can find more details about the Python API here.

CLI 
ir_datasets export trec-fair-2021/dev docs
[doc_id]    [title]    [text]    [marked_up_text]    [url]    [quality_score]    [geographic_locations]    [quality_score_disk]
...

You can find more details about the CLI here.

PyTerrier 
import pyterrier as pt
pt.init()
dataset = pt.get_dataset('irds:trec-fair-2021/dev')
# Index trec-fair-2021
indexer = pt.IterDictIndexer('./indices/trec-fair-2021')
index_ref = indexer.index(dataset.get_corpus_iter(), fields=['title', 'text', 'url'])

You can find more details about PyTerrier indexing here.

qrels
Query relevance judgment type:
TrecQrel: (namedtuple)
  1. query_id: str
  2. doc_id: str
  3. relevance: int
  4. iteration: str

Relevance levels

Rel.Definition
1relevant

Examples:

Python API 
import ir_datasets
dataset = ir_datasets.load("trec-fair-2021/dev")
for qrel in dataset.qrels_iter():
    qrel # namedtuple<query_id, doc_id, relevance, iteration>

You can find more details about the Python API here.

CLI 
ir_datasets export trec-fair-2021/dev qrels --format tsv
[query_id]    [doc_id]    [relevance]    [iteration]
...

You can find more details about the CLI here.

PyTerrier 
import pyterrier as pt
from pyterrier.measures import *
pt.init()
dataset = pt.get_dataset('irds:trec-fair-2021/dev')
index_ref = pt.IndexRef.of('./indices/trec-fair-2021') # assumes you have already built an index
pipeline = pt.BatchRetrieve(index_ref, wmodel='BM25')
# (optionally other pipeline components)
pt.Experiment(
    [pipeline],
    dataset.get_topics('text'),
    dataset.get_qrels(),
    [MAP, nDCG@20]
)

You can find more details about PyTerrier experiments here.