About a week left to apply to this postdoctoral position in Responsible AI/IR at @irglasgow.bsky.social

Details are below. Deadline to apply: 26th March

Come work with us – faculty position in Computer Networking in the School of Computing Science at the University of Glasgow www.jobs.gla.ac.uk/job/lecturer...

We have 2 tenure-track faculty openings in Machine Learning at @uofgcompsci.bsky.social; Applications are welcome in the general areas of AI & ML, which complement existing strengths in the @idaglasgow.bsky.social section.

Details at: jobs.gla.ac.uk/job/lecturer-s…

Deadline: 17 Feb 2025 at 23:45

GitHub - seanmacavaney/pyterrier-caching: Caching components for PyTerrier Caching components for PyTerrier. Contribute to seanmacavaney/pyterrier-caching development by creating an account on GitHub.

7/7. Finally, we've deprecated PyTerrier’s caching operator ~, as there is much more customisable caching in pyterrier-caching
github.com/seanmacavane...

6/7. Another cool addition by
@macavaney.bsky.social: integrating PyTerrier extension docs into pyterrier.readthedocs.io, including as pyterrier_dr (dense retrieval), pyterrier_doc2query, pyterrier_pisa etc. One place now has a full list of lots of SOTA extensions for retrieval.

5/7.
@macavaney.bsky.social
has been polishing pyterrier_dr (github.com/terrierteam/...) – our single-vector Dense Retrieval framework, for instance including PRF:

4/7. A complete rework of pipeline compilation by
@macavaney.bsky.social. PyTerrier compilation rewrites a pipeline by, e.g. applying rank cutoff earlier. So these two pipelines are equivalent, but potentially faster – .compile() allows that optimisation to happen automatically

3/7. Precomputation of common pipeline prefixes is something really 😎. For this example experiment comparing BM25 with BM25 >> monoT5, this means that only one BM25 retrieval is needed to evaluate both pipelines. Great for speeding up comparative experiments on large query sets!

2/7. Making transform_iter() into a first-class citizen of pt.Transformer – no need to manipulate dataframes – you can now write transformers that operate on a list of dicts. This (backwards compatible) change is big news as PyTerrier has been dataframe based from the outset.

GitHub - terrier-org/pyterrier: A Python framework for performing information retrieval experiments, building on http://terrier.org/ A Python framework for performing information retrieval experiments, building on http://terrier.org/ - terrier-org/pyterrier

We snuck out new releases in PyTerrier ecosystem in the last few weeks, with a number of 😍 changes…. 🧵👇 1/7
github.com/terrier-org/...
pyterrier.readthedocs.io

cc/ @irglasgow.bsky.social

Delighted to announce 'Semantically Proportioned nDCG for Explaining ColBERT’s Learning Process' with Ariane Mueller accepted to #ecir2025 Findings @irglasgow.bsky.social

Glad to share that our work (by Fanghzhen Tian and w/ @gdebasis.bsky.social and myself) "Is Relevance ‘Lost in Transmission’ from Retriever to Generator?" has been accepted to #ecir2025 as a full paper. See you next spring in Lucca 🙋🏻‍♂️ @irglasgow.bsky.social

Happy to share that our (w/ @grahammcdonald.bsky.social and @craigmacdonald.bsky.social ) work "Context Example Selection For LLM Generated Relevance Assessments" has been accepted to #ecir2025 as a full paper! 🎉 Exciting times! 🇮🇹
@irglasgow.bsky.social

medium.com/@carteret.ac...

I’m reminded of this letter, where it was stated that ACM (in this case) do not engage with
anonymous complaints

its very weird that page isn't signed.