Pith. sign in

REVIEW 16 cited by

BERT: A Review of Applications in Natural Language Processing and Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2103.11943 v1 pith:AAVB643T submitted 2021-03-22 cs.CL cs.AIcs.LG

M. V. Koroteev This is my paper
classification cs.CLcs.AIcs.LG
keywords languagemodelsreviewapplicationbertnaturalscientifictext
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this review, we describe the application of one of the most popular deep learning-based language models - BERT. The paper describes the mechanism of operation of this model, the main areas of its application to the tasks of text analytics, comparisons with similar models in each task, as well as a description of some proprietary models. In preparing this review, the data of several dozen original scientific articles published over the past few years, which attracted the most attention in the scientific community, were systematized. This survey will be useful to all students and researchers who want to get acquainted with the latest advances in the field of natural language text analysis.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory

    cs.CV 2026-05 unverdicted novelty 6.5 of 10

    Object hallucinations in MLLMs track multi-head spatial inconsistency and temporal visual-attention fade; AFIP corrects both via cross-head enrichment and gated historical reinjection, reducing CHAIR/POPE rates training-free.

  2. Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Zero-Fi aligns Wi-Fi CSI signal embeddings with CLIP text embeddings of LLM-generated activity descriptions, achieving 69.58% zero-shot accuracy on unseen activity classes.

  3. Remote Work: Driver or Deterrent of Digital Product Innovation

    econ.EM 2026-07 conditional novelty 6.0 of 10

    Staggered DiD on iOS apps shows remote-work adoption raises major releases and new features, preserves originality, lifts downloads, and works better for teams with prior modular OSS experience.

  4. OVITA: Open-Vocabulary Interpretable Trajectory Adaptations

    cs.RO 2025-08 conditional novelty 6.0 of 10

    OVITA uses LLM-generated Python code, a QP safety module, and user feedback to adapt robot trajectories from open-vocabulary natural language instructions, with an 81.4% user-study success rate.

  5. KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A graph-kernel comparison of LLM-derived and ground-truth knowledge graphs detects hallucinations and produces contrastive explanations.

  6. LIGHT: Multi-Modal Text Linking on Historical Maps

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A multimodal transformer that fuses language, image, and polygon geometry links recognized words into reading-order phrases on historical maps better than prior methods.

  7. Checked-In Secret Detection: Strings Are All You Need

    cs.CR 2026-08 conditional novelty 5.0 of 10

    Secretron, a dual-stream transformer and CNN detector using only string literals as context, achieves 0.9874 weighted F1 on SecretBench and stays above 0.95 F1 under obfuscation.

  8. TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

    cs.AI 2025-09 conditional novelty 5.0 of 10

    TableMind, a two-stage SFT-plus-RL agent trained on an 8B model, reports state-of-the-art results on three table reasoning benchmarks.

  9. Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation

    cs.IR 2025-06 conditional novelty 5.0 of 10

    CAR predicts each item as a chunk of semantic IDs plus a unique ID in one autoregressive step and reports large Recall@5 gains on three Amazon datasets.

  10. Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A new resolution-focused benchmark and an open-source native-resolution training framework show that preserving original image resolution improves VLM performance on fine-grained visual tasks.

  11. Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection

    cs.CR 2025-07 conditional novelty 4.0 of 10

    DeCoda combines LLM-based JavaScript deobfuscation with a cluster-aware graph transformer, reporting F1 scores of 94.6% and 97.7% on two malicious-code datasets.

  12. Large Language Models for EEG: A Comprehensive Survey and Taxonomy

    eess.SP 2025-06 conditional novelty 4.0 of 10

    A taxonomy and review of studies applying large language models to EEG signals, organized into four domains and three adaptation strategies.

  13. CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA

    cs.CL 2025-08 conditional novelty 3.0 of 10

    Fine-tuned LLaMA 3 8B reaches ~0.8 concept-level accuracy on MedHopQA development data but only ~0.5 exact match in validation and 0.0 to 0.2 on the test set.

  14. Scout: Leveraging Large Language Models for Rapid Digital Evidence Discovery

    cs.CR 2025-07 reject novelty 3.0 of 10

    Scout applies off-the-shelf LLMs and vision models to triage digital evidence, but only anecdotal examples are shown and accuracy is withheld.

  15. Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward

    cs.CV 2025-05 conditional novelty 3.0 of 10

    A survey paper reviews multimodal generative AI and autoregressive LLMs for text-driven human motion generation, with comparative tables of models, datasets, and metrics.

  16. Linguistics and Human Brain: A Perspective of Computational Neuroscience

    q-bio.NC 2026-02 unverdicted novelty 2.0 of 10

    A narrative review arguing that computational neuroscience, powered by LLM-based model–brain alignment, serves as the bridge between linguistic theory and neural data.

Pith tools