仇恨言论语料库

The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection

Fundamentals of Machine Learning (EEL5840) final project.

indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2

a state-of-the-art-level open visual language model | 多模态预训练模型

MENYO-20k Corpus in "The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation" in MT Summit 2021

CVPR 2021 Official Pytorch Code for UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

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

A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks

Implementation of "RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation".

Transformer model for Chinese-English translation.

[ACL 2023] S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering

AIR retriever for Multi-Hop QA (ACL 2020 paper)

Anserini is a Lucene toolkit for reproducible information retrieval research

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

A simple RNN based encoder decoder network for the task of machine translation from chinese to english.

Chinese-English Neural machine translation with Encoder-Decoder seq2seq model : Bidirection-GRU + Fasttext word embedding + Attention + K-Beam search + BLEU score

Attention-based RNN model for Chinese-English translation

Semantic Priming Across Many Languages (PSA Proposal)

An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of Human Behavior