docgen.templates.msmarco-doc-segmented-wp.template Maven / Gradle / Ivy

Go to download
# Anserini Regressions: MS MARCO Document Ranking

**Models**: various bag-of-words approaches on segmented documents with WordPiece tokenization

This page documents regression experiments on the [MS MARCO document ranking task](https://github.com/microsoft/MSMARCO-Document-Ranking), which is integrated into Anserini's regression testing framework.
Here we are using **WordPiece tokenization** (i.e., from BERT) on passages from the documents.
At retrieval time, we select the score of the highest-scoring passage from a document as the score for that document to produce a document ranking; this is known as the MaxP technique.
In general, effectiveness is lower than with "standard" Lucene tokenization for two reasons: (1) we're losing stemming, and (2) some terms are chopped into less meaningful subwords.

The exact configurations for these regressions are stored in [this YAML file](${yaml}).
Note that this page is automatically generated from [this template](${template}) as part of Anserini's regression pipeline, so do not modify this page directly; modify the template instead.

From one of our Waterloo servers (e.g., `orca`), the following command will perform the complete regression, end to end:

```
python src/main/python/run_regression.py --index --verify --search --regression ${test_name}
```

## Indexing

Typical indexing command:

```
${index_cmds}
```

The directory `/path/to/msmarco-doc-segmented/` should be a directory containing the segmented corpus in Anserini's jsonl format.
See [this page](experiments-msmarco-doc-doc2query-details.md) for how to prepare the corpus.

For additional details, see explanation of [common indexing options](common-indexing-options.md).

## Retrieval

Topics and qrels are stored in [`src/main/resources/topics-and-qrels/`](../src/main/resources/topics-and-qrels/).
The regression experiments here evaluate on the 5193 dev set questions.

After indexing has completed, you should be able to perform retrieval as follows:

```
${ranking_cmds}
```

Evaluation can be performed using `trec_eval`:

```
${eval_cmds}
```

## Effectiveness

With the above commands, you should be able to reproduce the following results:

${effectiveness}