Jimmy Lin

Expansion to new datasets

1

Does it make sense to expand Chatty Goose to new datasets? For example: + MANtIS - a multi-domain information seeking dialogues dataset: https://guzpenha.github.io/MANtIS/ + ClariQ - Search-oriented Conversational AI (SCAI)...

For @ronakice to work on...

As the title says...

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...

Implement Birch/MaxP variant

2

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` :)

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...

Currently only checks MD5. We store the file size in the `Dict`, so it'd be easy to check.

From @16BitNarwhal - pull latest master. Run: ``` java -cp `ls target/*-fatjar.jar` io.anserini.server.Application --server.port=8081 ``` Go to localhost:8081 and play with UI. Use the REST API: ``` curl -X GET...

From https://github.com/usnistgov/trec_eval - latest release tarball (v9.0.8) should go here? https://github.com/castorini/anserini-tools/tree/master/eval @jasper-xian I'll let you do this since you're working on https://github.com/castorini/anserini/pull/2324

With #26 - it'd be best to rename `convert_collection_to_jsonl.py` to `convert_passage_collection_to_jsonl.py` to disambiguate wrt `convert_doc_collection_to_jsonl.py`... Need to propagate changes to documentation in Anserini, so needs to be done carefully in...