yovakem Goto Github PK

allennlp

An open-source NLP research library, built on PyTorch.

demog-text-removal

dynet

DyNet: The Dynamic Neural Network Toolkit

forecasting_derailment

Code for paper "Dynamic Forecasting of Conversation Derailment"

generalized-procrustes-muse

inflection_in_context

interplm

kb

KnowBert -- Knowledge Enhanced Contextual Word Representations

m2scorer

MaxMatch (M^2) Scorer - Evaluation program for grammatical error correction systems.

msc_project

MSc project: What do character- and morpheme-level word embeddings learn about language?

muse

A library for Multilingual Unsupervised or Supervised word Embeddings

nl-augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

pytorch-beam-search-decoding

PyTorch implementation of beam search decoding for seq2seq models

rcsls

PyTorch implementation of the RCSLS cross-lingual word embedding alignment method

rnn-encoder-decoder-pytorch

RNN Encoder-Decoder in PyTorch

rwkv-lm

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

rwkv-v2-rnn-pile

RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.

simpletransformers

Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

transformers

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

ubar-multiwoz

AAAI 2021: "UBAR: Towards Fully End-to-End Task-Oriented Dialog System with GPT-2"

yovakem.github.io

personal page