Locally-running Teacher using AI.

Main repository for "CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters"

🐢 Open-Source Evaluation & Testing for AI & LLM systems

The offcial repository for 'CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos', SIGIR2022

Specialising Word Vectors for Lexical Entailment

The Attract-Repel algorithm presented in (Mrkšić et al., TACL 2017), with accompanying resources.

Counter-fitting Word Vectors to Linguistic Constraints

Skulpt is a Javascript implementation of the Python programming language

Visual primitives for the component age. Use the best bits of ES6 and CSS to style your apps without stress 💅

Codebase for testing whether hidden states of neural networks encode discrete structures.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Officially supported AllenNLP models

Animation engine for explanatory math videos

temporary word prism anonymous submission

Code and dataset of EMNLP 2020 paper "Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition"

LibKGE - A knowledge graph embedding library for reproducible research

Resources for WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking

Pre-trained Transformers for Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic ELECTRA)

Hyperbolic Embeddings

KnowBert -- Knowledge Enhanced Contextual Word Representations

Must-read Papers on pre-trained language models.

Bot for posting arXiv.org updates to twitter

LAnguage Model Analysis

Source code and Datasets of "Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors"

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"