Jieun-Enna

Smart_tigers

우리는.강력한.스마트.호랑이.둘.

awesome-machine-learning-interpretability

A curated list of awesome responsible machine learning resources.

DLFromScratch2

『밑바닥부터 시작하는 딥러닝 ❷』

deep-learning-from-scratch-2

『밑바닥부터 시작하는 딥러닝 ❷』(한빛미디어, 2019)

simpletod

Official repository for "SimpleTOD: A Simple Language Model for Task-Oriented Dialogue"

som-dst

SOM-DST: Efficient Dialogue State Tracking by Selectively Overwriting Memory (ACL 2020)

kgi-slot-filling

This is the code for our KILT leaderboard submissions (KGI + Re2G models).

HyKnow

End-to-end Task-oriented Dialog System with Hybrid Knowledge Management

neural-belief-tracker

Fully Statistical Neural Belief Tracker (Mrkšić and Vulić, ACL 2018)

CR-Walker

Conversational Recommender System with Tree-structured Graph Reasoning and Dialog Acts

100-nlp-papers

100 Must-Read NLP Papers

ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

ChatGPT

Reverse engineered ChatGPT API

metaseq

Repo for external large-scale work

AwesomeKorean_Data

한국어 데이터 세트 링크

ai-notes

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

PyNaver

네이버 API를 사용하기 위한 오픈소스 파이썬 라이브러리

GraphGPT

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

multimodal-speech-emotion

TensorFlow implementation of "Multimodal Speech Emotion Recognition using Audio and Text," IEEE SLT-18

Audio-and-text-based-emotion-recognition

A multimodal approach on emotion recognition using audio and text.

nsmc

Naver sentiment movie corpus

KoSentenceBERT-SKT

Sentence Embeddings using Siamese SKT KoBERT-Networks

KoBERT

Korean BERT pre-trained cased (KoBERT)

programmers_kdt_II

KDT 인공지능 교육과정 Material

ccpe

A dataset consisting of 502 English dialogs with 12,000 annotated utterances between a user and an assistant discussing movie preferences in natural language. It was collected using a Wizard-of-Oz methodology between two paid crowd-workers, where one worker plays the role of an 'assistant', while the other plays the role of a 'user'. The 'assistant' elicits the 'user’s' preferences about movies following a Coached Conversational Preference Elicitation (CCPE) method. The assistant asks questions designed to minimize the bias in the terminology the 'user' employs to convey his or her preferences as much as possible, and to obtain these preferences in natural language. Each dialog is annotated with entity mentions, preferences expressed about entities, descriptions of entities provided, and other statements of entities.

TG_CRS_Code

TG-ReDial

the dataset TG-ReDial

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Megatron-LM

Ongoing research training transformer models at scale

fairseq

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