mteb/EightTagsClustering.v2

Tasks

• text-classification

Citation text from the card

@inproceedings{dadas-etal-2020-evaluation,
  abstract = {Methods for learning sentence representations have been actively developed in recent years. However, the lack of pre-trained models and datasets annotated at the sentence level has been a problem for low-resource languages such as Polish which led to less interest in applying these methods to language-specific tasks. In this study, we introduce two new Polish datasets for evaluating sentence embeddings and provide a comprehensive evaluation of eight sentence representation methods including Polish and multilingual models. We consider classic word embedding models, recently developed contextual embeddings and multilingual sentence encoders, showing strengths and weaknesses of specific approaches. We also examine different methods of aggregating word vectors into a single sentence vector.},
  address = {Marseille, France},
  author = {Dadas, Slawomir  and
Pere{\\l}kiewicz, Micha{\\l}  and
Po{\\'s}wiata, Rafa{\\l}},
  booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
  editor = {Calzolari, Nicoletta  and
B{\\'e}chet, Fr{\\'e}d{\\'e}ric  and
Blache, Philippe  and
Choukri, Khalid  and
Cieri, Christopher  and
Declerck, Thierry  and
Goggi, Sara  and
Isahara, Hitoshi  and
Maegaard, Bente  and
Mariani, Joseph  and
Mazo, H{\\'e}l{\\`e}ne  and
Moreno, Asuncion  and
Odijk, Jan  and
Piperidis, Stelios},
  isbn = {979-10-95546-34-4},
  language = {English},
  month = may,
  pages = {1674--1680},
 

All datasets marked Possible licence conflict | JSON