Dynamic Topic Modeling for Cross-Corpus Temporal Analysis

• URL: http://arxiv.org/abs/2608.23284v1
• Date: Mon, 24 Aug 2026 14:08:54 GMT
• Title: Dynamic Topic Modeling for Cross-Corpus Temporal Analysis
• Abstract summary: Cross-corpus comparison is difficult because topics are often learned independently and aligned only after training.<n>We propose a D-ETM framework that first learns a common dynamic topic space over a merged multi-corpus collection, which we call the shared backbone.<n>We evaluate the framework on three temporally structured corpora spanning 97 years: the Corpus of Historical American English, Harvard Business Review, and International Labour Review.
• Score: 0.17188280334580194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic Embedded Topic Models (D-ETM) provide an interpretable framework for modeling temporal semantic evolution, but cross-corpus comparison remains difficult because topics are often learned independently and aligned only after training, a process that does not guarantee stable topic correspondence across corpora and time. To address this problem, we propose a D-ETM framework that first learns a common dynamic topic space over a merged multi-corpus collection, which we call the shared backbone, then introduces corpus-specific residual adaptation around the frozen backbone without creating separate latent topic spaces. This design preserves a shared topic index for cross-corpus comparison while allowing each corpus to specialize lexically. We evaluate the framework on three temporally structured corpora spanning 97 years: the Corpus of Historical American English, Harvard Business Review, and International Labour Review. Residual adaptation improves corpus-specific fit relative to the shared backbone while preserving the same-index cross-corpus topic trajectories, achieving substantially stronger alignment than full fine-tuning from the same backbone, with $97.5 \pm 0.7\%$ versus $17.9 \pm 1.1\%$ trajectory Retrieval@1, as well as stronger alignment than independent training with post-hoc Hungarian matching. These results suggest that incorporating topic alignment into the model can support more stable over-time cross-corpus comparisons while retaining corpus-specific lexical variation.

Related papers

• A Shared IPTC Topic Space for Cross-Source Topic Modelling [3.368151533620041]
  This paper presents a reproducible framework that places corpora in a single shared topic space defined by a taxonomy.<n>The framework was developed and selected on a controlled New York Times 2011 corpus.
  arXiv  Detail & Related papers  (2026-06-25T10:32:41Z)
• From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors [25.32575172623139]
  Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs.<n>We propose a training-free and model-agnostic compression framework that selects a compact set of sentences guided by structural graph priors.<n>Our method constructs a sparse hybrid sentence graph that combines mutual k-NN semantic edges with short-range sequential edges.
  arXiv  Detail & Related papers  (2026-04-25T12:40:54Z)
• Anchoring and Rescaling Attention for Semantically Coherent Inbetweening [9.061831090604324]
  Generative inbetweening (GI) seeks to synthesize realistic intermediate frames between the first and last stages of a sequence.<n>We give semantic and temporal guidance from the paths and text onto each intermediate frame through Keyframe-anchored Attention Bias.<n>We also better frame consistency with Rescaled Temporal RoPE, which allows self-attention to enforces more faithfully.
  arXiv  Detail & Related papers  (2026-03-18T12:11:02Z)
• Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning [56.6025512458557]
  Motion-language retrieval aims to bridge the semantic gap between natural language and human motion.<n>Existing approaches predominantly focus on aligning entire motion sequences with global textual representations.<n>We propose a novel Pyramidal Shapley-Taylor (PST) learning framework for fine-grained motion-language retrieval.
  arXiv  Detail & Related papers  (2026-01-29T16:00:12Z)
• PALUM: Part-based Attention Learning for Unified Motion Retargeting [53.17113525688095]
  Remotion between characters with different skeleton structures is a fundamental challenge in computer animation.<n>We present a novel approach that learns common motion representations across diverse skeleton topologies.<n>Experiments demonstrate superior performance in handling diverse skeletal structures while maintaining motion realism and semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-12T07:29:44Z)
• Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition [64.56321246196859]
  We propose a novel dyNamically Evolving dUal skeleton-semantic syneRgistic framework.<n>We first construct the spatial-temporal evolving micro-prototypes and integrate dynamic context-aware side information.<n>We introduce the spatial compression and temporal memory mechanisms to guide the growth of spatial-temporal micro-prototypes.
  arXiv  Detail & Related papers  (2024-11-18T05:16:11Z)
• Interactive Topic Models with Optimal Transport [75.26555710661908]
  We present EdTM, as an approach for label name supervised topic modeling. EdTM models topic modeling as an assignment problem while leveraging LM/LLM based document-topic affinities.
  arXiv  Detail & Related papers  (2024-06-28T13:57:27Z)
• NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpus [23.49376007047965]
  It remains a question that how simultaneous interpretation (SI) data affects simultaneous machine translation (SiMT) We introduce NAIST-SIC-Aligned, which is an automatically-aligned parallel English-Japanese SI dataset. Our results show that models trained with SI data lead to significant improvement in translation quality and latency over baselines.
  arXiv  Detail & Related papers  (2023-04-23T23:03:58Z)
• Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition [8.905895607185135]
  Transformer shows great potential to model the correlation of important joints. Existing Transformer-based methods cannot capture the correlation of different joints between frames. Atemporal-recognition module is proposed to capture the relationship of different joints in consecutive frames.
  arXiv  Detail & Related papers  (2022-01-08T16:03:01Z)
• MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency [72.82534577726334]
  We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. Our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
  arXiv  Detail & Related papers  (2020-06-22T08:50:09Z)
• Skeleton-Aware Networks for Deep Motion Retargeting [83.65593033474384]
  We introduce a novel deep learning framework for data-driven motion between skeletons. Our approach learns how to retarget without requiring any explicit pairing between the motions in the training set.
  arXiv  Detail & Related papers  (2020-05-12T12:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.