EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Questions Are All You Need to Train a Dense Passage Retriever

Devendra Singh Sachan, Mike Lewis, Dani Yogatama, Luke Zettlemoyer, Joelle Pineau, Manzil Zaheer

Transactions of the Association for Computational Linguistics · 20.06.2023 · 11 · 600-616

DOI: 10.1162/tacl_a_00564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 20.06.2023. Verfasst von Devendra Singh Sachan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g., questions and potential answer passages). It uses a new passage-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evidence passages, and (2) the passages are then used to compute the probability of reconstructing the original question. Training for retrieval based on question reconstruction enables effective unsupervised learning of both passage and question encoders, which can be later incorporated into complete Open QA systems without any further finetuning. Extensive experiments demonstrate that ART obtains state-of-the-art results on multiple QA retrieval benchmarks with only generic initialization from a pre-trained language model, removing the need for labeled data and task-specific losses.1 Our code and model checkpoints are available at: https://github.com/DevSinghSachan/art.

Zitieren

APA

Sachan, D. S., Lewis, M., Yogatama, D., Zettlemoyer, L., Pineau, J., & Zaheer, M. (2023). Questions Are All You Need to Train a Dense Passage Retriever. Transactions of the Association for Computational Linguistics, 11, 600-616. https://doi.org/10.1162/tacl_a_00564

Vancouver

Sachan DS, Lewis M, Yogatama D, Zettlemoyer L, Pineau J, Zaheer M. Questions Are All You Need to Train a Dense Passage Retriever. Transactions of the Association for Computational Linguistics. 2023;11:600-616. doi:10.1162/tacl_a_00564

BibTeX
@article{Sachan2023,
  author = {Sachan, Devendra Singh and Lewis, Mike and Yogatama, Dani and Zettlemoyer, Luke and Pineau, Joelle and Zaheer, Manzil},
  title = {Questions Are All You Need to Train a Dense Passage Retriever},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  volume = {11},
  pages = {600--616},
  doi = {10.1162/tacl_a_00564}
}
Kostenlos starten →