paper-with-me

Papers

BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding

2019-09-11 · NeurIPS Workshop Document_Intelligen 2019 12 · Timo I. Denk, Christian Reisswig

For understanding generic documents, information like font sizes, column layout, and generally the positioning of words may carry semantic information that is crucial for solving a downstream document intelligence task. Our novel BERTgrid, which is based on Chargrid by Katti et al. (2018), represents a document as a grid of contextualized word piece embedding vectors, thereby making its spatial structure and semantics accessible to the processing neural network. The contextualized embedding vectors are retrieved from a BERT language model. We use BERTgrid in combination with a fully convolutional network on a semantic instance segmentation task for extracting fields from invoices. We demonstrate its performance on tabulated line item and document header field extraction.

📄 PDF Abstract BibTeX arXiv:1909.04948

Code (2)

dhiraa/tener tf
sam-ai/BertGrid

Tasks

Instance SegmentationLanguage ModelingLanguage ModellingSemantic Segmentation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents

2021-05-25 · WeiHong Lin, Qifang Gao, Lei Sun, Zhuoyao Zhong 외

Recent grid-based document representations like BERTgrid allow the simultaneous encoding of the textual and layout information of a document in a 2D feature map so that state-of-the-art image segmentation and/or object d…

Image SegmentationKey Information Extractionobject-detectionObject Detection+2

ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents

2024-09-23 · Furkan Pala, Mehmet Yasin Akpınar, Onur Deniz, Gülşen Eryiğit

Multimodal key information extraction (KIE) models have been studied extensively on semi-structured documents. However, their investigation on unstructured documents is an emerging research topic. The paper presents an a…

Key Information Extractionnamed-entity-recognitionNamed Entity Recognition

Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddings

2023-05-16 · Roberto Martínez-Cruz, Debanjan Mahata, Alvaro J. López-López, José Portela

In this study, we investigate using graph neural network (GNN) representations to enhance contextualized representations of pre-trained language models (PLMs) for keyphrase extraction from lengthy documents. We show that…

Graph Neural NetworkKeyphrase Extraction

Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence

2020-04-08 · ACL 2021 5 · Federico Bianchi, Silvia Terragni, Dirk Hovy

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder …

Sentence EmbeddingsTopic ModelsVariational Inference

CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling

2023-05-16 · Zheng Fang, Yulan He, Rob Procter

Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualiz…

Document ClassificationLanguage ModellingNatural Language UnderstandingNER+3