IBM / span-selection-pretrainingLinks
Code to create pre-training data for a span selection pre-training task inspired by reading comprehension and an effort to avoid encoding general knowledge in the transformer network itself.
☆30Updated 3 years ago
Alternatives and similar repositories for span-selection-pretraining
Users that are interested in span-selection-pretraining are comparing it to the libraries listed below
Sorting:
- An original implementation of ACL 2019, "Compositional Questions Do Not Necessitate Multi-hop Reasoning" (Single-hop Reading Comprehensio…☆58Updated 5 years ago
- The official implementation of ACL 2020, "Logic-Guided Data Augmentation and Regularization for Consistent Question Answering".☆71Updated last year
- This is the repo for the paper "Revealing the Importance of Semantic Retrieval for Machine Reading at Scale".☆60Updated 5 years ago
- Implementation of the EMNLP 2020 paper "Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition".☆52Updated 4 years ago
- ☆70Updated 2 years ago
- The implementation of the paper "Harvesting and Refining Question-Answer Pairs for Unsupervised QA"☆33Updated 4 years ago
- ☆64Updated 2 years ago
- Code and Data for our EMNLP 2020 paper titled 'Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multiho…☆28Updated 3 years ago
- [ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling☆71Updated 2 years ago
- [EMNLP 2020] Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading☆36Updated 2 years ago
- ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhi…☆49Updated 4 years ago
- An original implementation of EMNLP 2019, "A Discrete Hard EM Approach for Weakly Supervised Question Answering"☆136Updated 5 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆57Updated 2 years ago
- Enhancing AMR-to-Text Generation with Dual Graph Representations (implementation for the EMNLP-IJCNLP-2019 paper)☆22Updated 5 years ago
- ☆69Updated 4 years ago
- The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2…☆89Updated 11 months ago
- ☆21Updated 3 years ago
- PathNet model for Multi-hop Reading Comprehension (https://arxiv.org/pdf/1811.01127.pdf)☆21Updated 4 years ago
- Progressively Pretrained Dense Corpus Index for Open-Domain QA and Information Retrieval☆43Updated 2 years ago
- Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension☆104Updated 5 years ago
- Code and data for the paper: Answer-based Adversarial Training for Generating Clarification Questions☆43Updated 4 years ago
- NABERT model for solving the DROP dataset☆26Updated 6 years ago
- The source code for ACL 2020 paper Exclusive Hierarchical Decoding for Deep Keyphrase Generation☆55Updated 2 years ago
- AIR retriever for Multi-Hop QA (ACL 2020 paper)☆30Updated 5 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆69Updated 3 years ago
- Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.☆29Updated last year
- Denoising methods for distantly-labeled entity typing data☆31Updated 2 years ago
- Cross-Lingual Machine Reading Comprehension (EMNLP 2019)☆68Updated 5 years ago
- Code and Models for paper "AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning. Han Guo, Ramakanth Pasunuru, and Mohit Ba…☆24Updated 6 years ago
- Tools and datasets for Aristo Leaderboards☆42Updated 4 years ago