[NAACL'22-Findings] Dataset for "Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training"

Sentires: A Toolkit for Phrase-level Sentiment Analysis

The code for paper "ProQA: Structural Prompt-based Pre-training for Unified Question Answering"

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

The Excel add-in for creating LaTeX tables

Multilingual Sentence & Image Embeddings with BERT

Language-Agnostic SEntence Representations

Fusion-in-Decoder

Pytorch Seq2Seq framework

Open-Retrieval Conversational Machine Reading: A new setting & OR-ShARC dataset

IJCAI 2021 Tutorial & code for Retrospective Reader for Machine Reading Comprehension (AAAI 2021)

A simple tmux configuration for nested tmux sessions

This is the official repository for NAACL 2021, "XOR QA: Cross-lingual Open-Retrieval Question Answering".

TGLS: Unsupervised Text Generation by Learning from Search

[EMNLP 2020] Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

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

Learning Vim and Vimscript doesn't have to be hard. This is the guide that you're looking for 📖

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The information of computer journal

Wikipedia tools (for Humans): easily extract data from Wikipedia, Wikidata, and other MediaWikis

ACL2020 Tutorial: Open-Domain Question Answering

Code for the SIGIR 2020 paper "A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss"

Google Research

Tutorials on training and testing retrieval-based models (DrQA & DPR)