paper
A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts
paperactiveprovisional
a-study-of-temporal-fusion-strategies-for-named-entity-recognition-in-historical-texts-3d26d2a7·1 events·first seen 39h agoAliases: A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts
More like this (12)
Connectionist Temporal ClassificationNAMESAKES: Probing Identity Memorization in Text-to-Image ModelsEIT-NLPFlashbackCL: Mitigating Temporal Forgetting in Federated LearningSame Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language ModelsWhich Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and RepresentationSingle and Multi Truth Data Fusion using Large Language ModelsHow Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV with Claim-Grounded Typed CitationsWhen Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense RetrievalAn Empirical Analysis of Factual Errors in Human-Written Text and its ApplicationHow Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple MitigationBeyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering
Recent events (1)
Temporal fusion strategies for NER in historical texts favor late fusion mechanisms
A new arXiv preprint systematically evaluates how temporal metadata can be embedded into transformer-based NER models for historical texts, comparing absolute vs. relative temporal representations and early vs. late fusion mechanisms including cross-attention, adapters, and concatenation. Experiments on French and German historical datasets show that late fusion strategies yield more robust and temporally generalizable performance, especially on early and noisy text periods. The work addresses a narrow but underexplored challenge of diachronic NLP where entity surface forms drift across time.