adamlin120

LongChat

Official repository for LongChat and LongEval

llm-eval

LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models

custom

ask-the-doc

Ask the Doc app built using Langchain and Streamlit.

dataset_difficulty

DialEvalMetrics

llm-platform

Few-Shot-Intent-Detection

Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines and results.

MultiWOZ_Evaluation

Unified MultiWOZ evaluation scripts for the context-to-response task.

tts_asr_server

Zero-Shot-DST

Zero-shot dialogue state tracking (DST)

TextRL

Reinforcement learning in text generation with transformers

cross-ontology-dst

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

adl-hw1-sample-code

.dotfiles

cldst

DSTC9-Track2

Multi-Domain Task-Completion Dialog Challenge II

NTU_AMMAI_CDFSL

The source code of NTU-AMMAI-CDFSL

dotfiles

:wrench: .files, including ~/.macos — sensible hacker defaults for macOS

ML2018SPRING

ADL_2019_NTU

Application of Deep Learning, Spring 2019, CSIE 5431 @ National Taiwan University https://www.csie.ntu.edu.tw/~miulab/s107-adl/

Zero-shot_Classification_of_News_Title

Zero-shot Classification of News Title - Final Project for IRTM NTU 2018