SentenceTransformer based on CALDISS-AAU/DA-BERT_Old_News_V1
This is a sentence-transformers model finetuned from CALDISS-AAU/DA-BERT_Old_News_V1. It is an early version of a model meant to assist in segmenting ENO.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: CALDISS-AAU/DA-BERT_Old_News_V1
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 dimensions
Training Details
Training Dataset
Unnamed Dataset
- Size: 27,869 training samples
- Columns:
sentence_0,sentence_1, andlabel - Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 4 tokens
- mean: 41.42 tokens
- max: 401 tokens
- min: 4 tokens
- mean: 41.21 tokens
- max: 286 tokens
- min: 0.0
- mean: 0.46
- max: 1.0
- Samples:
sentence_0 sentence_1 label 6) Paa Hjørnet af Integaden og lilie Kongensgade ligge to store Trækasser, sog afspærre Passagen, og truer dem, der i Mørke kunde løbe paa dem.7) Paa Østergade er der intet Bræt over den Rendesteen der kommer ud fra Per Madsens Gang og med en dyb Kisterende overskærer Fortoget.1.0Ganske Fattige undervises for intet, og Seminaristerne bibringer han sin Methode.Ved et af ham selv opfundet Tegnsprog giver han sin Undervisning Indgang.1.0
- Downloads last month
- -
Model tree for JohanHeinsen/Old_News_Segmentation_SBERT_V0
Base model
CALDISS-AAU/DA-BERT_Old_News_V1