arXiv:2502.11973v3 Announce Type: replace 
Abstract: Uniform Meaning Representation (UMR) is a recently developed graph-based semantic representation, which expands on Abstract Meaning Representation (AMR) in a number of ways, in particular through the inclusion of document-level information and multilingual flexibility. In order to effectively adopt and leverage UMR for downstream tasks, efforts must be placed toward developing a UMR technological ecosystem. Though only a small amount of UMR annotations have been produced to date, in this work, we investigate the first approaches to producing text from multilingual UMR graphs. Exploiting the structural similarity between UMR and AMR graphs and the wide availability of AMR technologies, we introduce (1) a baseline approach which passes UMR graphs to AMR-to-text generation models, (2) a pipeline conversion of UMR to AMR, then using AMR-to-text generation models, and (3) a fine-tuning approach for both foundation models and AMR-to-text generation models with UMR data. Our best performing models achieve multilingual BERTscores of 0.825 for English and 0.882 for Chinese, a promising indication of the effectiveness of fine-tuning approaches for UMR-to-text generation even with limited UMR data.

أدت التطورات الأخيرة في تمثيل المعنى الموحد (UMR) إلى استكشاف طرق لتوليد النصوص من الرسوم البيانية UMR متعددة اللغات، مما يعزز قدرات التمثيل الدلالي في معالجة اللغة الطبيعية. تهدف هذه الأبحاث إلى تطوير نظام تكنولوجي حول UMR، بالاعتماد على الأطر الموجودة لتمثيل المعنى المجرد (AMR).

Los recientes avances en la Representación de Significado Uniforme (UMR) han llevado a la exploración de métodos para generar texto a partir de gráficos UMR multilingües, mejorando así las capacidades de representación semántica en el procesamiento del lenguaje natural. Esta investigación tiene como objetivo desarrollar un ecosistema tecnológico en torno a la UMR, basándose en los marcos existentes de la Representación de Significado Abstracto (AMR).

Des avancées récentes dans la représentation sémantique uniforme (UMR) ont conduit à l'exploration de méthodes pour générer du texte à partir de graphes UMR multilingues, améliorant ainsi les capacités de représentation sémantique dans le traitement du langage naturel. Cette recherche vise à développer un écosystème technologique autour de l'UMR, en s'appuyant sur les cadres existants de la représentation sémantique abstraite (AMR).

Recent advancements in Uniform Meaning Representation (UMR) have led to the exploration of methods for generating text from multilingual UMR graphs, enhancing the capabilities of semantic representation in natural language processing. This research aims to develop a technological ecosystem around UMR, building on the existing frameworks of Abstract Meaning Representation (AMR).

Generating Text from Uniform Meaning Representation

arXiv:2503.04971v2 Announce Type: replace 
Abstract: Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates privacy-preserving FM fine-tuning on resource-constrained local devices by offloading partial FM computations to edge servers, enabling device-edge synergistic fine-tuning. Practical edge networks often host multiple SFL tenants to support diversified downstream tasks. However, existing research primarily focuses on single-tenant SFL scenarios, and lacks tailored incentive mechanisms for multi-tenant settings, which are essential to effectively coordinate self-interested local devices for participation in various downstream tasks, ensuring that each SFL tenant's distinct FM fine-tuning requirements (e.g., FM types, performance targets, and fine-tuning deadlines) are met. To address this gap, we propose a novel Price-Incentive Mechanism (PRINCE) that guides multiple SFL tenants to offer strategic price incentives, which solicit high-quality device participation for efficient FM fine-tuning. Specifically, we first develop a bias-resilient global SFL model aggregation scheme to eliminate model biases caused by independent device participation. We then derive a rigorous SFL convergence bound to evaluate the contributions of heterogeneous devices to FM performance improvements, guiding the incentive strategies of SFL tenants. Furthermore, we model inter-tenant device competition as a congestion game for Stackelberg equilibrium (SE) analysis, deriving each SFL tenant's optimal incentive strategy. Extensive simulations involving four representative SFL tenant types (ViT, BERT, Whisper, and LLaMA) across diverse data modalities (text, images, and audio) demonstrate that PRINCE accelerates FM fine-tuning by up to 3.07x compared to state-of-the-art approaches, while consistently meeting fine-tuning performance targets.

تم اقتراح آلية جديدة للتسعير والتحفيز (PRINCE) لتحسين التعلم الفيدرالي متعدد المستأجرين (SFL) لنماذج الأساس (FMs) مثل GPT-4، مما يتيح ضبطًا فعالًا على الأجهزة ذات الموارد المحدودة مع الحفاظ على الخصوصية. تعالج هذه الآلية تحديات التنسيق التي تواجه عدة مستأجرين في SFL لديهم احتياجات ضبط متنوعة.

Se ha propuesto un nuevo Mecanismo de Precio-Incentivo (PRINCE) para mejorar el Aprendizaje Federado de Múltiples Inquilinos (SFL) para Modelos de Fundación (FMs) como GPT-4, permitiendo un ajuste eficiente en dispositivos con recursos limitados mientras se mantiene la privacidad. Este mecanismo aborda los desafíos de coordinación que enfrentan múltiples inquilinos de SFL con diversas necesidades de ajuste.

Un nouveau mécanisme de prix incitatif (PRINCE) a été proposé pour améliorer l'apprentissage fédéré à plusieurs locataires (SFL) pour les modèles de fondation (FMs) tels que GPT-4, permettant un ajustement efficace sur des appareils à ressources limitées tout en préservant la vie privée. Ce mécanisme répond aux défis de coordination rencontrés par plusieurs locataires SFL ayant des besoins d'ajustement divers.

A novel Price-Incentive Mechanism (PRINCE) has been proposed to enhance Multi-Tenant Split Federated Learning (SFL) for Foundation Models (FMs) like GPT-4, enabling efficient fine-tuning on resource-constrained devices while maintaining privacy. This mechanism addresses the coordination challenges faced by multiple SFL tenants with diverse fine-tuning needs.

Generating Text from Uniform Meaning Representation

Was this article worth reading? Share it

Humanize AI

Airparser

Supametas.AI

Uwear

ZeroGPT.org

AI Humanizer

Ready to build your own newsroom?