Akari Asai

self-rag. This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

OpenScholar. This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

learning_to_retrieve_reasoning_paths. The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".

ScholarQABench. This repository contains ScholarQABench data and evaluation pipeline.

ATTEMPT. This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)

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

logic_guided_qa. The official implementation of ACL 2020, "Logic-Guided Data Augmentation and Regularization for Consistent Question Answering".

CORA. This is the official implementation of NeurIPS 2021 "One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval".

evidentiality_qa. The official implemetation of "Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks" (NAACL 2022).

OpenScholar_ExpertEval. This repository contains expert evaluation interface and data evaluation script for the OpenScholar project.

extractive_rc_by_runtime_mt. Code and datasets of "Multilingual Extractive Reading Comprehension by Runtime Machine Translation"

unanswerable_qa. The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

Artificial_Intelligence. Jupyter Notebook

HappyDB. A corpus of 100,000 happy moments

document-qa-MLQA. Python

word-embeddings-benchmarks. Package for evaluating word embeddings. This is forked from kududak/word-embeddings-benchmarks

pytorch-pretrained-BERT. 📖The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.

wikiextractor. A tool for extracting plain text from Wikipedia dumps

papers. Summaries of machine learning papers