Name: Luca Soldaini
Type: User
Company: @allenai @queerai
Bio: Research Scientist at @allenai in the OLMo & Semantic Scholar teams.
Interested in NLP and Information Retrieval.
Twitter: soldni
Location: Seattle, WA, USA
Blog: http://soldaini.net/
Luca Soldaini's Projects
ACL Rolling Review website
Compare AMD and NVIDIA GPUs when training same LM
Article extraction benchmark: dataset and evaluation scripts
Lightweight wrapper to display Bing image of the day
Joint Slot Filling and Intent Detection via Capsule Neural Networks (ACL'19) https://arxiv.org/abs/1812.09471
:rainbow: To each context its own shell color
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
Simple demo Flask application for "COSC280 - Intro to Databases"
Single method library that receives a dictionary (of dictionaries of dictionaries of ...) and returns a csv table ready to be written to file
Resources for the "What's New? Summarizing Contributions in Scientific Literature" paper
DKPro C4CorpusTools is a collection of tools for processing CommonCrawl corpus, including Creative Commons license detection, boilerplate removal, language detection, and near-duplicate removal.
A collection of scripts that build docker images for various use-cases.
Fork of Dolma toolkit for February 2024 ARR submission.
my dot files
:scream: A dark theme for Vim
Repository for the EACL 2023 conference website
A struct config parser that you can set up in the time it takes to make an espresso.
serve files from s3 using flask
WIP evaluation of ForeCite. See https://github.com/allenai/forecite for details.
A simple fuzzy matching set for python strings
update A records on gandi
Sync Google Drive Folder with PDFs to a Notion database. One way sync only!
Topic Modelling for Humans
A fast, simple graph drawing and data plotting app for OS X and iPad.
HomeKit support for the impatient
Verify if URL is in HON
A simple resume theme for Hugo
Prototype for ML hydra config