PulseAugur / Brief
EN
LIVE 21:45:04

Brief

last 24h
[3/3] 221 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · arXiv cs.CL English(EN) ·

    RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian

    Researchers have introduced RoIt-XMASA, a new dataset designed for multilingual sentiment analysis in Romanian and Italian. This dataset includes 36,000 labeled reviews across books, movies, and music, along with over 200,000 unlabeled samples. To tackle cross-lingual and cross-domain challenges, they developed a multi-target adversarial training framework that achieved an F1-score of 66.23% with XLM-R, surpassing the baseline by 4.64%. AI

    IMPACT Enhances multilingual NLP capabilities, particularly for under-resourced languages like Romanian and Italian.

  2. TOOL · arXiv cs.AI English(EN) ·

    Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

    Researchers have developed a new framework called Context-Aware Layer-wise Integrated Gradients (CA-LIG) to improve the explainability of Transformer models. This framework offers a unified, hierarchical approach that computes layer-wise attributions and fuses them with attention gradients. CA-LIG aims to provide more faithful, context-sensitive, and semantically coherent explanations of how these models make decisions across various tasks and architectures. AI

    IMPACT Provides more comprehensive and reliable explanations for Transformer decision-making, advancing interpretability.

  3. RESEARCH · arXiv cs.CL English(EN) · · [2 sources]

    A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text

    Researchers have developed a new, reproducible pipeline for creating a Universal Dependencies-style parsing resource for Katharevousa Greek parliamentary text. This workflow addresses the limitations of current NLP tools for historical Greek documents, integrating OCR reconstruction, LLM-assisted annotation, and automated validation. The resulting dataset and methodology aim to make historical parliamentary archives more accessible for NLP research. AI

    IMPACT Enables better NLP analysis of historical Greek parliamentary documents, potentially unlocking new research in linguistics and history.