Pith. sign in

REVIEW 5 cited by

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 2106.12978 v1 pith:XS4PUEAR submitted 2021-06-24 cs.LG cs.CL

Unsupervised Topic Segmentation of Meetings with BERT Embeddings

classification cs.LG cs.CL
keywords topicunsupervisedsegmentationapproachesbertdatasetsembeddingsmeeting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large datasets. In this paper we show how previous unsupervised topic segmentation methods can be improved using pre-trained neural architectures. We introduce an unsupervised approach based on BERT embeddings that achieves a 15.5% reduction in error rate over existing unsupervised approaches applied to two popular datasets for meeting transcripts.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation

    cs.CL 2026-04 unverdicted novelty 7.0

    Introduces the AMI-ME dataset of 2,459 human-annotated segments and an LLM-judge framework that scores meeting effectiveness as the rate of objective achievement within topical segments.

  2. Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload

    cs.SE 2026-05 conditional novelty 6.0

    VisDoc uses GenAI to restructure OSS onboarding documentation according to CTML principles, yielding higher task success and lower cognitive load in a small newcomer study.

  3. Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation

    cs.CL 2026-04 conditional novelty 6.0

    An LLM-as-judge framework scores meeting transcript segments for objective achievement over time, validated on a new 2,459-segment human-annotated dataset from the AMI Corpus.

  4. CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation

    cs.CL 2026-05 unverdicted novelty 5.0

    CobSeg is a multi-branch architecture for dialogue topic segmentation that separates semantic continuity from lexical transitions, uses boundary informativeness weighting and corpus-derived cues, and reports metric ga...

  5. Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload

    cs.SE 2026-05 unverdicted novelty 5.0

    VisDoc uses a GenAI pipeline grounded in CTML to restructure OSS onboarding docs, with small evaluations showing higher task success and lower cognitive load.