AristotelisPap / Question-Answering-with-BERT-and-Knowledge-Distillation
Fine-tuned BERT on SQuAd 2.0 Dataset. Applied Knowledge Distillation (KD) and fine-tuned DistilBERT (student) using BERT as the teacher model. Reduced the size of the original BERT by 40%.
☆25Updated 4 years ago
Alternatives and similar repositories for Question-Answering-with-BERT-and-Knowledge-Distillation:
Users that are interested in Question-Answering-with-BERT-and-Knowledge-Distillation are comparing it to the libraries listed below
- Source codes of Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction☆43Updated 3 years ago
- The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)☆52Updated 2 years ago
- ☆33Updated last year
- Official PyTorch Implementation of SSMix (Findings of ACL 2021)☆62Updated 3 years ago
- pyTorch implementation of Recurrence over BERT (RoBERT) based on this paper https://arxiv.org/abs/1910.10781 and comparison with pyTorch …☆80Updated 2 years ago
- ☆25Updated 4 years ago
- Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper☆52Updated last year
- DSTC9 Submission☆18Updated 3 years ago
- Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (ACL 2021)☆30Updated 2 years ago
- The PyTorch implementation of ReCoSa(the Relevant Contexts with Self-attention) for dialogue generation using the multi-head attention an…☆22Updated last year
- The sources codes of the DR-BERT model and baselines☆37Updated 3 years ago
- PyTorch implementations of algorithms for knowledge distillation.☆57Updated 4 years ago
- [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning☆93Updated 2 years ago
- Use BERT for Question Answering and finetune train with SQuAD 2.0☆15Updated 5 years ago
- Implementation of paper "Learning to Encode Text as Human-Readable Summaries using GAN"☆66Updated 5 years ago
- Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems☆22Updated 3 years ago
- ☆38Updated 2 years ago
- Benchmarking various Deep Learning models such as BERT, ALBERT, BiLSTMs on the task of sentence entailment using two datasets - MultiNLI …☆28Updated 4 years ago
- TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition (ACL 2021)☆48Updated 2 years ago
- ☆42Updated 4 years ago
- KE-Dialogue: Injecting knowledge graph into a fully end-to-end dialogue system.☆46Updated 3 years ago
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆46Updated 2 years ago
- ☆26Updated 2 months ago
- Self-supervised NER prototype - updated version (69 entity types - 17 broad entity groups). Uses pretrained BERT models with no fine tuni…☆79Updated 2 years ago
- Abstractive summarization using Bert2Bert framework.☆31Updated 4 years ago
- Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling☆10Updated 2 years ago
- Transformer Encoder with Char information for text classification☆15Updated 5 years ago
- SlotRefine: A Fast Non-Autoregressive Model forJoint Intent Detection and Slot Filling☆48Updated 3 years ago
- Codes for our CCL 2021 paper: Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Network…☆24Updated 3 years ago
- Question Answering task using Deep Learning on SQuAD dataset☆20Updated 2 years ago