Pith. sign in

REVIEW 1 cited by

VIBE: Topic-Driven Temporal Adaptation for Twitter Classification

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.10191 v4 pith:YG2LYG2S submitted 2023-10-16 cs.CL

classification cs.CL
keywords dataclassificationvibeadaptationadaptivebottleneckfeaturesfuture
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language features are evolving in real-world social media, resulting in the deteriorating performance of text classification in dynamics. To address this challenge, we study temporal adaptation, where models trained on past data are tested in the future. Most prior work focused on continued pretraining or knowledge updating, which may compromise their performance on noisy social media data. To tackle this issue, we reflect feature change via modeling latent topic evolution and propose a novel model, VIBE: Variational Information Bottleneck for Evolutions. Concretely, we first employ two Information Bottleneck (IB) regularizers to distinguish past and future topics. Then, the distinguished topics work as adaptive features via multi-task training with timestamp and class label prediction. In adaptive learning, VIBE utilizes retrieved unlabeled data from online streams created posterior to training data time. Substantial Twitter experiments on three classification tasks show that our model, with only 3% of data, significantly outperforms previous state-of-the-art continued-pretraining methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Concept Incongruence: An Exploration of Time and Death in Role Playing

    cs.CL 2025-05 conditional novelty 5.0 of 10

    LLMs asked to role-play dead historical figures rarely abstain from answering post-death questions, and their factual accuracy drops due to poorly encoded death states and role-playing-induced shifts in temporal repre...

Pith tools