Pith. sign in

REVIEW 3 cited by

Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence

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 2004.03974 v2 pith:WXKWXMOJ submitted 2020-04-08 cs.CL

Federico Bianchi , Silvia Terragni , Dirk Hovy This is my paper · ORCID
classification cs.CL
keywords modelstopicneuralbettercoherencecoherentcontextualizedembeddings
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic models and recent neural models. Our results indicate that future improvements in language models will translate into better topic models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Continual Neural Topic Model

    cs.LG 2025-08 reject novelty 5.0 of 10

    CoNTM is an online neural topic model whose global topics are a running average of time-slice topics; the paper's no-forgetting claim is asserted without a forgetting test.

  2. NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    NGTM generates graphs by sampling substructures from learned topic-specific distributions and assembling them, achieving competitive quality with interpretable, controllable topics.

  3. Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling

    cs.CL 2025-06 conditional novelty 5.0 of 10

    DALTA adapts a variational topic model from a high-resource source domain to a low-resource target domain via adversarial latent alignment, separate decoders, and a consistency loss, with a claimed generalization bound.

Pith tools