Stanford, California

Nelson Liu

Elite
@nelson-liu

@stanfordnlp CS PhD student.

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

387

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

324

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

212

pytorch-manylinux-binaries. Shell

141

evaluating-verifiability-in-generative-search-engines. Companion repo for "Evaluating Verifiability in Generative Search Engines".

87

cython-crash-course. A quick intro to Cython for Python users who don't know C

34

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

23

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

21

lexical-semantic-recognition. Python

18

website. HTML

13

pytorch-paper-classifier. 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 .

12

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

9

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

7

word2color. Given a description of a color, return its closest standard HTML4 color.

7

phonesthemes. 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.

5

nlp-phd-vis. Visualizations on NLP PhD applications

4

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

3

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

3

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

3

quoref-annotation. HTML

2

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

2

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

2

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

1

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

1

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

1

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

1

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

1

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

1

llama-recipes. 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

1

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

1

nltk. NLTK Source

1

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

1

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

1

ical2org. Convert iCal-format calendars into a file of Emacs org-mode entries

1

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

1

deep_qa_experiments. Scala framework for running experiments with allenai/deep_qa

1
36
Apply