mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
5cfa72a130
# Bibtex integration Wrap bibtexparser to retrieve a list of docs from a bibtex file. * Get the metadata from the bibtex entries * `page_content` get from the local pdf referenced in the `file` field of the bibtex entry using `pymupdf` * If no valid pdf file, `page_content` set to the `abstract` field of the bibtex entry * Support Zotero flavour using regex to get the file path * Added usage example in `docs/modules/indexes/document_loaders/examples/bibtex.ipynb` --------- Co-authored-by: Sébastien M. Popoff <sebastien.popoff@espci.fr> Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
14 lines
2.2 KiB
BibTeX
14 lines
2.2 KiB
BibTeX
@inproceedings{shen2021layoutparser,
|
|
title = {LayoutParser: A unified toolkit for deep learning based document image analysis},
|
|
author = {Shen, Zejiang and Zhang, Ruochen and Dell, Melissa and Lee, Benjamin Charles Germain and Carlson, Jacob and Li, Weining},
|
|
booktitle = {Document Analysis and Recognition--ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5--10, 2021, Proceedings, Part I 16},
|
|
pages = {131--146},
|
|
year = {2021},
|
|
organization = {Springer},
|
|
editor = {Llad{\'o}s, Josep
|
|
and Lopresti, Daniel
|
|
and Uchida, Seiichi},
|
|
file = {layout-parser-paper.pdf},
|
|
abstract = {{Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of important innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout detection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digitization pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io.",
|
|
isbn="978-3-030-86549-8}},
|
|
} |