English
Related papers

Related papers: Document-as-Image Representations Fall Short for S…

200 papers

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

Information Retrieval · Computer Science 2021-08-20 Hongyin Tang , Xingwu Sun , Beihong Jin , Jingang Wang , Fuzheng Zhang , Wei Wu

Large Language Models (LLMs) have demonstrated impressive capabilities in answering questions, but they lack domain-specific knowledge and are prone to hallucinations. Retrieval Augmented Generation (RAG) is one approach to address these…

Computation and Language · Computer Science 2024-10-30 Monica Riedler , Stefan Langer

Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstrated on image representations. Recent works aiming at…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Guillaume Couairon , Matthieu Cord , Matthijs Douze , Holger Schwenk

Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…

Information Retrieval · Computer Science 2026-01-29 Hongyi Cai

Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD), particularly those dominated by lengthy textual content like research journal articles. Existing studies primarily focus on real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Yihao Ding , Kaixuan Ren , Jiabin Huang , Siwen Luo , Soyeon Caren Han

Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text…

Multimedia · Computer Science 2019-06-21 Christian Otto , Matthias Springstein , Avishek Anand , Ralph Ewerth

A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words…

Information Retrieval · Computer Science 2016-02-04 Bhaskar Mitra , Eric Nalisnick , Nick Craswell , Rich Caruana

Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved content. In this work, we introduce the text-image interleaved…

Computation and Language · Computer Science 2025-02-19 Xin Zhang , Ziqi Dai , Yongqi Li , Yanzhao Zhang , Dingkun Long , Pengjun Xie , Meishan Zhang , Jun Yu , Wenjie Li , Min Zhang

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take…

Computation and Language · Computer Science 2022-01-11 Shicheng Tan , Shu Zhao , Yanping Zhang

The quality of a document is affected by various factors, including grammaticality, readability, stylistics, and expertise depth, making the task of document quality assessment a complex one. In this paper, we explore this task in the…

Computation and Language · Computer Science 2019-01-15 Aili Shen , Bahar Salehi , Timothy Baldwin , Jianzhong Qi

Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practice, however, retrieval outcomes systematically reflect perspectival biases: deviations shaped by…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

Information Retrieval · Computer Science 2019-05-03 Tolgahan Cakaloglu , Christian Szegedy , Xiaowei Xu

Joint embeddings between medical imaging modalities and associated radiology reports have the potential to offer significant benefits to the clinical community, ranging from cross-domain retrieval to conditional generation of reports to the…

Machine Learning · Computer Science 2018-11-28 Tzu-Ming Harry Hsu , Wei-Hung Weng , Willie Boag , Matthew McDermott , Peter Szolovits

Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples…

Computation and Language · Computer Science 2020-10-27 Natraj Raman , Armineh Nourbakhsh , Sameena Shah , Manuela Veloso

We address the extraction of mathematical statements and their proofs from scholarly PDF articles as a multimodal classification problem, utilizing text, font features, and bitmap image renderings of PDFs as distinct modalities. We propose…

Artificial Intelligence · Computer Science 2024-10-14 Shrey Mishra , Antoine Gauquier , Pierre Senellart

Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Or Perel , Oron Anschel , Omri Ben-Eliezer , Shai Mazor , Hadar Averbuch-Elor

Images and text co-occur constantly on the web, but explicit links between images and sentences (or other intra-document textual units) are often not present. We present algorithms that discover image-sentence relationships without relying…

Computation and Language · Computer Science 2019-09-04 Jack Hessel , Lillian Lee , David Mimno

In this article we study the problem of document image representation based on visual features. We propose a comprehensive experimental study that compares three types of visual document image representations: (1) traditional so-called…

Computer Vision and Pattern Recognition · Computer Science 2016-12-05 Gabriela Csurka , Diane Larlus , Albert Gordo , Jon Almazan

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document…

Computation and Language · Computer Science 2022-03-17 Shunyu Zhang , Yaobo Liang , Ming Gong , Daxin Jiang , Nan Duan

Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction. In…

Digital Libraries · Computer Science 2018-06-01 Noah Siegel , Nicholas Lourie , Russell Power , Waleed Ammar