Robust PDF Document Conversion Using Recurrent Neural Networks
IBM Research（IBM研究院）
Nikolaos Livathinos, Cesar Berrospi, Maksym Lysak, Viktor Kuropiatnyk, Ahmed Nassar, Andre Carvalho, Michele Dolfi, Christoph Auer, Kasper Dinkla, Peter Staar
备注：
9 pages, 2 tables, 4 figures, uses aaai21.sty. Accepted at the "Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21)". Received the "IAAI-21 Innovative Application Award"
The number of published PDF documents has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature. We demonstrate how a sequence of PDF printing commands can be used as input into a neural network and how the network can learn to classify each printing command according to its structural function in the page. This approach has three advantages: First, it can distinguish among more fine-grained labels (typically 10-20 labels as opposed to 1-5 with visual methods), which results in a more accurate and detailed document structure resolution. Second, it can take into account the text flow across pages more naturally compared to visual methods because it can concatenate the printing commands of sequential pages. Last, our proposed method needs less memory and it is computationally less expensive than visual methods. This allows us to deploy such models in production environments at a much lower cost. Through extensive architectural search in combination with advanced feature engineering, we were able to implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels. The best model we achieved is currently served in production environments on our Corpus Conversion Service (CCS), which was presented at KDD18 (arXiv:1806.02284). This model enhances the capabilities of CCS significantly, as it eliminates the need for human annotated label ground-truth for every unseen document layout. This proved particularly useful when applied to a huge corpus of PDF articles related to COVID-19.
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
Faculty of Engineering, University of Porto（葡萄牙波尔图大学工程学院）；Department of Business Administration, University of Maia（马亚大学商业管理系）；LIACC—Artificial Intelligence and Computer Science Laboratory, University of Porto（葡萄牙波尔图大学人工智能与计算机科学实验室）；Department of Communication Sciences and Information Technologies, University of Maia（马亚大学通讯科学与信息科技系）；School of Health, Polytechnic of Porto（波尔图理工学院健康学院）；School of Technology and Management, Polytechnic Institute of Maia（马亚理工学院技术与管理学院）
Probabilistic Deterministic Finite Automata and Recurrent Networks, Revisited
W. M. Keck Science Department, Claremont McKenna, Scripps, and Pitzer College（克莱蒙特·麦肯纳学院、斯克里普斯学院和皮策学院 W. M. 凯克科学系）；University of California, Davis（加州大学戴维斯分校）
Fully Analog Resonant Recurrent Neural Network via Metacircuit
Institute of Humanoid Robots, CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China（机器人研究院、材料力学行为与设计国家重点实验室、精密机械与精密仪器系、中国科学技术大学）；State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University（机械系统与振动国家重点实验室、上海交通大学）
On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification
Viterbi Faculty of Electrical and Computing Engineering, Technion - Israel Institute of Technology（技术学院-以色列理工学院电子与计算工程学院）；College of Engineering and Physical Sciences, Aston University（阿斯顿大学工程与物理科学学院）
Implementing Neural Network-Based Equalizers in a Coherent Optical Transmission System Using Field-Programmable Gate Arrays
Aston Institute of Photonic Technologies, Aston University（阿斯顿大学阿斯顿光子技术研究所）；Infinera R&D（Infinera研发部）；Infinera Unipessoal, Lda（Infinera有限责任公司）；AMD Research（AMD研究院）
