EntilZha
Research Scientist @ FAIR Labs (@facebookresearch) NLP, Retrieval-Augmented Language Models, QA, Data + Eval; PhD in CS from UMD, Berkeley CS Grad;
@facebookresearch, FAIR LabsSeattle, WA
Pinned Repositories
docker-workshop
Docker workshop going over how to create a set of microservices
entilzha.github.io
Personal webpage sourcecode
GrappaRDD
Resilient Distributed Datasets from Apache Spark with distributed shared memory using Grappa
PyFunctional
Python library for creating data pipelines with chain functional programming
pygraph
CLI interface to python graphviz
spark-s3
spark package to natively read S3 files instead of through hadoop, improving speed
spot-price-reporter
Fetch and plot AWS spot pricing history
wikidata-rust
Fast rust-based parser for wikidata dumps
qb
QANTA Quiz Bowl AI
EntilZha's Repositories
EntilZha/PyFunctional
Python library for creating data pipelines with chain functional programming
EntilZha/entilzha.github.io
Personal webpage sourcecode
EntilZha/slurm-tools
EntilZha/acl-miniconf-old
EntilZha/acl-service-handbook
Community sourced handbook for how to propose/create/run *ACL workshops
EntilZha/dotfiles-old
Configuration files (dotfiles) repo
EntilZha/music-theory
EntilZha/overseer
EntilZha/acl-2023
Repository for the ACL 2023 conference website
EntilZha/acl-login
EntilZha/acl-miniconf-fork
Repository containing general version of ACL miniconf
EntilZha/aclpubcheck
Tools for checking ACL paper submissions
EntilZha/altair
Declarative statistical visualization library for Python
EntilZha/career
EntilZha/collaborative-experts
Video embeddings for retrieval with natural language queries
EntilZha/docsets
EntilZha/dynabench
Dynamic Adversarial Benchmarking platform
EntilZha/eacl-2024-miniconf
EntilZha/FiD
Fusion-in-Decoder
EntilZha/flax
Flax is a neural network library for JAX that is designed for flexibility.
EntilZha/irt-leaderboard
Leaderboards are widely used in NLP and push the field forward. While leaderboards are a straightforward ranking of NLP models, this simplicity can mask nuances in evaluation items (examples) and subjects (NLP models). Rather than replace leaderboards, we advocate a re-imagining so that they better highlight if and where progress is made. Building on educational testing, we create a Bayesian leaderboard where latent subject skill and latent item difficulty predict correct responses. Using this model, we analyze the reliability of leaderboards. Afterwards, we show the model can guide what annotate, identify annotation errors, detect overfitting, and identify informative examples.
EntilZha/jbg-web
Source code for Jordan Boyd-Graber's academic webpage.
EntilZha/multidim-irt
EntilZha/pedroai
Package for python utility functions
EntilZha/react-music
EntilZha/rlmeta
RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.
EntilZha/scholar.hasfailed.us
Google Scholar is a trans-exclusionary site. Don't use it. Help us demand change.
EntilZha/sl-testing
EntilZha/slurm-utils
EntilZha/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.