Edit model card


This is a doc2query model based on T5 (also known as docT5query).

It can be used for:

  • Document expansion: You generate for your paragraphs 20-40 queries and index the paragraphs and the generates queries in a standard BM25 index like Elasticsearch, OpenSearch, or Lucene. The generated queries help to close the lexical gap of lexical search, as the generate queries contain synonyms. Further, it re-weights words giving important words a higher weight even if they appear seldomn in a paragraph. In our BEIR paper we showed that BM25+docT5query is a powerful search engine. In the BEIR repository we have an example how to use docT5query with Pyserini.
  • Domain Specific Training Data Generation: It can be used to generate training data to learn an embedding model. On SBERT.net we have an example how to use the model to generate (query, text) pairs for a given collection of unlabeled texts. These pairs can then be used to train powerful dense embedding models.


from transformers import T5Tokenizer, T5ForConditionalGeneration

model_name = 'doc2query/msmarco-t5-base-v1'
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)

text = "Python is an interpreted, high-level and general-purpose programming language. Python's design philosophy emphasizes code readability with its notable use of significant whitespace. Its language constructs and object-oriented approach aim to help programmers write clear, logical code for small and large-scale projects."

input_ids = tokenizer.encode(text, max_length=320, truncation=True, return_tensors='pt')
outputs = model.generate(


print("\nGenerated Queries:")
for i in range(len(outputs)):
    query = tokenizer.decode(outputs[i], skip_special_tokens=True)
    print(f'{i + 1}: {query}')

Note: model.generate() is non-deterministic. It produces different queries each time you run it.


This model fine-tuned google/t5-v1_1-base for 31k training steps (about 4 epochs on the 500k training pairs from MS MARCO). For the training script, see the train_script.py in this repository.

The input-text was truncated to 320 word pieces. Output text was generated up to 64 word pieces.

This model was trained on a (query, passage) from the MS MARCO Passage-Ranking dataset.

Downloads last month
Hosted inference API
Text2Text Generation
This model can be loaded on the Inference API on-demand.

Dataset used to train doc2query/msmarco-t5-base-v1