Nelson Liu

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Various models and code (Manhattan LSTM, Siamese LSTM + Matching Layer, BiMPM) for the paraphrase identification task, specifically with the Quora Question Pairs dataset.

A toolkit for evaluating the linguistic knowledge and transferability of contextual representations. Code for "Linguistic Knowledge and Transferability of Contextual Representations" (NAACL 2019).

No description.

Companion repo for "Evaluating Verifiability in Generative Search Engines".

A quick intro to Cython for Python users who don't know C

Dump the text of the Gigaword dataset into a single file, for use with language modeling (and other!) toolkits

Code for the paper "Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets", to be presented at NAACL 2019.

No description.

No description.

A simple model for classifying papers by academic venue (AI/ML/ACL), given a title and abstract. Bare-metal PyTorch port of https://github.com/allenai/allennlp-as-a-library-example .

:microphone: DubHacks 2015 project. Decode sign language using the Leap Motion, and speak it!

Given a description of a color, return its closest standard HTML4 color.

:helicopter: Controlling a Parrot AR 2 Drone with Thalmic Labs Myo. PennApps 2015 Spring.

Code for the paper "Discovering Phonesthemes with Sparse Regularization", to be presented at the NAACL 2018 Workshop on Subword and Character Level Models in NLP.

Visualizations on NLP PhD applications

Code for the paper "LSTMs Exploit Linguistic Attributes of Data", presented at the ACL 2018 Workshop on Representation Learning for NLP.

:money_with_wings: The MIT Kerberos-integrated social wallet. Winner of BitComp 2014 Improving MIT Award.

Repository for materials for informal and slightly less informal talks and tutorials

A natural language processing toolkit using state-of-the-art deep learning models.

No description.

:phone: Built @ MHacks 6 -- An SMS based natural language question and answer system.

A fast, simple and lightweight Bloom filter library for Python, implemented in Rust.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

A crate for uploading files to Google cloud storage, and for generating download urls.

A collaborative platform for reproducible research (web interface and CLI).

🏎 A set of primitives to build simple, flexible, WAI-ARIA compliant React autocomplete, combobox or select dropdown components.

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's Readability.js package or in pure-python mode.

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Code accompanying "Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words"

Convert iCal-format calendars into a file of Emacs org-mode entries

NLTK Source

Author implementation of "Learning Recurrent Span Representations for Extractive Question Answering" (Lee et al. 2016)

Fast, flexible and easy to use probabilistic modelling in Python.

Scala framework for running experiments with allenai/deep_qa

A conda-smithy repository for pytorch-pretrained-bert.

Streaming WARC/ARC library for fast web archive IO

A robust web archive analytics toolkit

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

A library to analyze PyTorch traces.

A high-throughput and memory-efficient inference and serving engine for LLMs

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

A set of Python scripts for preprocessing the Wikidata JSON dump and running simple queries in an efficient manner.

Painless hash link routing for React applications.

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

Distills the DOM

Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper

Model API for GALACTICA

Production repository for the all-new Advantage360 Professional using ZMK engine

Fuzzy String Matching in Python

a wrapper event that listen & control URL changes

OpenTelemetry Python API and SDK

The repository for high quality TypeScript type definitions.

WAI-ARIA compliant React autosuggest component

Python forced alignment

Contrastive Language-Image Pretraining

A conda-smithy repository for editdistance.

Faking your webcam background under GNU/Linux, now supports background blurring, animated background, colour map effect, hologram effect and on-demand processing.

Methods of training NLP models to ignored biased strategies

LegalCrawler: A tool for automated scraping of English legal corpora

NAACL2021 website

The SAIL blog

Huggingface Transformers + Adapters = ❤️

Few-shot Learning of GPT-3

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

Continuous builder and binary build scripts for pytorch

Data and software for building the ACL Anthology.

NAACL SRW 2021 Website

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

Convert ical .ics file to org-mode

Official Stanford NLP Python Library for Many Human Languages

Wikidata client library for Python

Officially supported AllenNLP models

Code for using and evaluating SpanBERT.

No description.

No description.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Conda documentation

Using deep learning to answer Aristo's science questions

Bidirectional Attention Flow

End-to-end Neural Coreference Resolution

No description.

LSTM and QRNN Language Model Toolkit for PyTorch

No description.

A conda-smithy repository for allennlp.

A conda-smithy repository for jsonnet.

TensorFlow code and pre-trained models for BERT

Tensorflow implementation of contextualized word representations from bi-directional language models

A neural parser for QA-SRL.

A py.test plugin for adding to the PYTHONPATH from pytest.ini.

A conda-smithy repository for pyhocon.

Open Source Neural Machine Translation in PyTorch

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

An unstable, still under construction, but updated version of the Parser repo, used for Stanford's submission in the CoNLL17 shared task.

No description.

No description.

Computation using data flow graphs for scalable machine learning

Utility scripts for common ML club activities

Miscellaneous scripts and benchmarks used in developing various scikit-learn features

Repo for blog posts @ http://blog.nelsonliu.me/

scikit-learn: machine learning in Python