Add new clustering tasks for a new domain (Engineering)

[mehrzadshm]

The datasets are associated with this research work (under review): Benchmarking pre-trained text embedding models in aligning built asset information

The work introduces 6 tasks, in three main types: clustering, retrieval, and reranking. To keep the PR concise for review only added the two clustering tasks (for now).

HuggingFace links to datasets :

• builtbench-clustering-p2p
• builtbench-clustering-s2s

Adding datasets checklist

Reason for dataset addition: This dataset points to a new domain, i.e., "Engineering" (more specifically related to architecture, construction, and built asset management)

• I have run the following models on the task (adding the results to the pr). These can be run using the mteb -m {model_name} -t {task_name} command.
  • sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
  • intfloat/multilingual-e5-small
• I have checked that the performance is neither trivial (both models gain close to perfect scores) nor random (both models gain close to random scores).
• If the dataset is too big (e.g. >2048 examples), considering using self.stratified_subsampling() under dataset_transform()
• I have filled out the metadata object in the dataset file (find documentation on it here).
• Run tests locally to make sure nothing is broken using make test.
• Run the formatter to format the code using make lint.

Looking forward to your feedback!

[Samoed]

It seems you want to add missing tasks to benchmark. You can follow adding_a_benchmark doc to fully integrate it

[mehrzadshm]

Makes perfect sense; I'll be adding other tasks and putting it all together as a new benchmark