pygaggle
pygaggle copied to clipboard
castorini
a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.22 to 1.26.5. Release notes Sourced from urllib3's releases. 1.26.5 :warning: IMPORTANT: urllib3 v2.0 will drop support for Python 2: Read more in the v2.0 Roadmap Fixed...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [pyyaml](https://github.com/yaml/pyyaml) from 3.12 to 5.4. Changelog Sourced from pyyaml's changelog. 5.4 (2021-01-19) yaml/pyyaml#407 -- Build modernization, remove distutils, fix metadata, build wheels, CI to GHA yaml/pyyaml#472 -- Fix for...
Bumps [websockets](https://github.com/aaugustin/websockets) from 5.0.1 to 9.1. Changelog Sourced from websockets's changelog. 9.1 ... May 27, 2021 .. note:: **Version 9.1 fixes a security issue introduced in version 8.0.** Version 8.0...
Before segment each document into passages by applying a sliding window of 10 sentences with a stride of five, may be some extra pre-processing method using regular expression? We simply...
Apparently, @jacklin64 and @justram tell me that we have our own ColBERT, which is a re-implementation... we should sort through reproduction and what goes where... I think our ColBERT reranker...
Bunch of experiments but we're not really storing any of these files, we should so others can use these scores and intermediate files for each of our experiments easily without...
I was looking into adding duo support (k-way ranking potentially) for MSMARCO and TREC-CAR. For RelevanceExample, I was wondering if we can have documents as Union(List[Text], List[List[Text]]) instead of just...
We should probably implement our own variant of Birch/BERT-MaxP in PyGaggle - + Birch: https://www.aclweb.org/anthology/D19-1352/ + BERT-MaxP: https://dl.acm.org/doi/10.1145/3331184.3331303 Let's call it `MonoBirchP` :)
Make the `T5CachedModelLoader` class more general to include *BERT -- should just be a few lines.
See https://github.com/castorini/pyserini/blob/master/setup.py#L3 I think it's a good idea to keep the README on PyPI separate from (and simpler than) the README in the repo. That way, we also don't have...