finetuning experiments on summarization tasks for Hebrew

A character-wise tokenizer for morphologically rich languages

An NLP pipeline for Hebrew

Level-based Foraging (LBF): A multi-agent environment for RL

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Risk board game implementation

Repository for our paper “Subverting the Jewtocracy”: Online Antisemitism Detection Using MultimodalDeep Learning

Genetic algorithms and the game of Risk

Code for Stanford CS224u

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

A research tool for the Iterated Prisoner's Dilemma

Code to accompany "Human-Level Performance in No-Press Diplomacy via Equilibrium Search", published at ICLR 2021

Repository for ACL 2020 Paper: "It Takes Two to Lie: One to Lie, and One to Listen"

Named Entity (NER) annotations of the Hebrew Treebank (Haaretz newspaper) corpus, including: morpheme and token level NER labels, nested mentions, and more.

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Evaluating Text Representations on Lexical Composition

The MWE identification system, MTLB-STRUCT, participated in the PARSEME 1.2 Shared Task on semi-supervised identification of verbal multiword expressions.

node.js interface to the Google word2vec tool

Standard python pickle, thinly wrapped with standard compression libraries

An OpenAI gym for Risk style board game (Not affiliated with Risk! or Hasbro)

Pure Python Spell Checking http://pyspellchecker.readthedocs.io/en/latest/

Contextual word checker for better suggestions