Dies ist unsere neueste Auswahl an weltweiten Veröffentlichungen und Patenten in englischer Sprache zum Thema Natural Language Processing (NLP), die in zahlreichen wissenschaftlichen Online-Zeitschriften zu den Themen natürliche Sprachverarbeitung, Tokenisierung, Stemming, Lemmatisierung, Part-of-Speech, Named Entity Recognition und Sentiment Analysis veröffentlicht wurden.
Voice-based conversation artificial intelligence for point-of-sale systems
Patent published on the 2025-03-06 in WO under Ref WO2025049246 by PREDICTSPRING INC [US] (Mangtani Nitin [us], Garimella Sandilya [us], Chadalawada Viswanth [us], Sahu Madhav [us])
Abstract: A conversational artificial intelligence (Al) point-of-sale (POS) system uses generative Al to help a store associate complete tasks in a retail environment. This POS system combines four technologies: speech recognition; natural language processing; acting in response to verbal command in the context of a retail store and a POS device; and providing bi-directional and fully conversational responses. The Al, which runs in an app on a smartphone, tablet, or other mobile device, uses a machine lea[...]
Our summary: Conversational AI POS system uses generative AI to assist store associates in retail tasks, combining speech recognition, natural language processing, and bi-directional responses. The AI, running on mobile devices, utilizes ML models trained on support tickets and product documentation to understand dependencies and provide appropriate responses.
voice-based conversation, artificial intelligence, point-of-sale systems, generative AI
Patent
Image interpretation model development
Patent published on the 2025-03-06 in WO under Ref WO2025048865 by SYNTHESIS HEALTH INC [CA] (Reicher Murray [ca], Kaura Deepak [ca])
Abstract: An image classification model, e.g., a neural network model, may be trained on a set of training medical imaging exams each including a training report and a training medical image. A model generation module or device may, for each of the training medical imaging exams: use finding item criteria to reorganize text of the training report into a list of finding items, each associated with text extracted from the training report text, use natural language processing to analyze the resultant text as[...]
Our summary: Training a neural network model on medical imaging exams with associated finding items and classifications extracted from training reports.
image interpretation, model development, neural network, medical imaging
Patent
regulatory challenges, technical solutions, and practical pathways
Published on 2025-02-19 by @OXFORD
Abstract: AbstractThis paper thoroughly explores the complex interplay between blockchain technology and the General Data Protection Regulation (GDPR) of the European Union, alongside the substantial challenges and potential opportunities stemming from their interaction. While the challenges of decentralization and immutability in blockchain are well-documented, this paper advances the discussion by incorporating legal developments, such as evolving interpretations of joint controllership and new advisory[...]
Our summary: This paper examines the regulatory challenges and technical solutions in aligning blockchain technology with GDPR principles, proposing practical pathways for compliance through innovative solutions such as chameleon hashes and zero-knowledge proofs.
blockchain technology, General Data Protection Regulation (GDPR), compliance challenges, innovative solutions
Publication
Metric-Free Learning Network with Dual Relations Propagation for Few-Shot Aspect Category Sentiment Analysis
Published on 2024-02-03 by Shiman Zhao, Yutao Xie, Wei Chen, Tengjiao Wang, Jiahui Yao, Jiabin Zheng @MIT
Abstract: Few-shot Aspect Category Sentiment Analysis (ACSA) is a crucial task for aspect-based sentiment analysis, which aims to detect sentiment polarity for a given aspect category in a sentence with limited data. However, few-shot learning methods focus on distance metrics between the query and support sets to classify queries, heavily relying on aspect distributions in the embedding space. Thus, they suffer from overlapping distributions of aspect embeddings caused by irrelevant sentiment noise among[...]
Our summary: Metric-Free Learning Network with Dual Relations Propagation for Few-Shot Aspect Category Sentiment Analysis. Crucial task for aspect-based sentiment analysis. Proposes metric-free method using Dual Relations Propagation. Achieves improvement in accuracy and F1 score.
learning, network, relations, propagation, sentiment
Publication
