EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval

Ohad Rubin, Jonathan Berant

Transactions of the Association for Computational Linguistics · 30.09.2024 · 12 · 1197-1213

DOI: 10.1162/tacl_a_00693 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 30.09.2024. Verfasst von Ohad Rubin und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the ability of the LM and the retriever to adapt to one another. In this work, we propose the Retrieval-Pretrained Transformer (RPT), an architecture and training procedure for jointly training a retrieval-augmented LM from scratch and applying it to the task of modeling long texts. Given a recently generated text chunk in a long document, the LM computes query representations, which are then used to retrieve earlier chunks in the document, located potentially tens of thousands of tokens before. Information from retrieved chunks is fused into the LM representations to predict the next target chunk. We train the retriever component with a semantic objective, where the goal is to retrieve chunks that increase the probability of the next chunk, according to a reference LM. We evaluate RPT on four long-range language modeling tasks, spanning books, code, and mathematical writing, and demonstrate that RPT improves retrieval quality and subsequently perplexity across the board compared to strong baselines.

Zitieren

APA

Rubin, O., & Berant, J. (2024). Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval. Transactions of the Association for Computational Linguistics, 12, 1197-1213. https://doi.org/10.1162/tacl_a_00693

Vancouver

Rubin O, Berant J. Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval. Transactions of the Association for Computational Linguistics. 2024;12:1197-1213. doi:10.1162/tacl_a_00693

BibTeX
@article{Rubin2024,
  author = {Rubin, Ohad and Berant, Jonathan},
  title = {Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  volume = {12},
  pages = {1197--1213},
  doi = {10.1162/tacl_a_00693}
}
Kostenlos starten →