Jiao, Wenxiang

Is-ChatGPT-A-Good-Translator. A preliminary evaluation of ChatGPT/GPT-4 for machine translation.

ParroT. The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

HiGRUs. Implementation of the paper "Hierarchical GRU for Utterance-level Emotion Recognition" in NAACL-2019.

AGHMN. Implementation of the paper "Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network" in AAAI-2020.

UncSamp. Implementation of our paper "Self-training Sampling with Monolingual Data Uncertainty for Neural Machine Translation" to appear in ACL-2021.

Data-Rejuvenation. Implementation of our paper "Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation" in EMNLP-2020.

InstructMT. A collection of instruction data and scripts for machine translation.

WMT2022-Large-Scale-African. Introduction to "Tencent’s Multilingual Machine Translation System for WMT22 Large-Scale African Languages".

Pre-CODE. Implementation of our paper "Exploiting Unsupervised Data for Emotion Recognition in Conversations" in the Findings of EMNLP-2020.

LLM-Hands-On. Re-organized codes for developing LLM-based Chatbots, including DataProc, SFT, DPO, Demo, etc.

Multimodal-Feature-Extraction. A detailed description on how to extract and align text, audio, and video features at word-level.

ResNet-Video-Features. Temporal video features extracted from ImageNet pre-trained ResNet-152.

Awesome-Chinese-Instruction-Datasets. 中文 Instruction 相关数据集整理

BERT-Text-Features. BERT-Text-Features for Tokenized Transcripts from P2FA.