microsoft / KEARLinks
Official code for achieving human parity on CommonsenseQA with External Attention
☆109Updated 2 years ago
Alternatives and similar repositories for KEAR
Users that are interested in KEAR are comparing it to the libraries listed below
Sorting:
- Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"☆108Updated last year
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆146Updated 3 years ago
- ☆117Updated 3 years ago
- Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 20…☆109Updated 3 years ago
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆168Updated 2 years ago
- This repository maintains the QAConv dataset, a question-answering dataset on informative conversations including business emails, panel …☆81Updated 8 months ago
- Few-shot NLP benchmark for unified, rigorous eval☆91Updated 2 years ago
- ☆114Updated last week
- Code and Data for EMNLP2020 Paper "KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation"☆149Updated 4 years ago
- Knowledge Computing group - MSRA☆87Updated last year
- ☆66Updated 3 years ago
- The autoregressive information extraction system GenIE (Generative Information Extraction) implemented in PyTorch.☆104Updated 2 years ago
- This repository implements our ACL Findings 2022 research paper RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Sh…☆133Updated 2 years ago
- Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations☆132Updated 3 weeks ago
- Investigating Pretrained Language Models for Graph-to-Text Generation☆146Updated 3 years ago
- ☆105Updated 4 months ago
- Source code for paper "Learning from Noisy Labels for Entity-Centric Information Extraction", EMNLP 2021☆55Updated 3 years ago
- An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"☆131Updated 3 years ago
- Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"☆91Updated 2 years ago
- Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"☆64Updated 3 years ago
- Source for the ACL 2021 Findings paper "Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models"☆50Updated 2 years ago
- ☆222Updated last year
- Multi-hop dense retrieval for question answering☆215Updated 3 years ago
- Code and Data for ICLR2021 Paper "Open Question Answering over Tables and Text"☆154Updated last year
- The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2…☆89Updated 10 months ago
- PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxi…☆106Updated last year
- code of CycleGT☆87Updated 2 years ago
- Structured Prediction as Translation between Augmented Natural Languages☆134Updated 3 years ago
- Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"☆67Updated 3 years ago
- ☆90Updated last year