AristotelisPap / Question-Answering-with-BERT-and-Knowledge-DistillationLinks
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
Sorting:
- Improved version of GECToR☆59Updated 2 years ago
- pyTorch implementation of Recurrence over BERT (RoBERT) based on this paper https://arxiv.org/abs/1910.10781 and comparison with pyTorch …☆82Updated 2 years ago
- ☆42Updated 3 years ago
- ☆59Updated 2 years ago
- Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper☆134Updated 2 years ago
- Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines …☆147Updated 2 years ago
- "End-to-End Abstractive Summarization for Meetings" paper - Unofficial PyTorch Implementation☆53Updated 2 years ago
- CharBERT: Character-aware Pre-trained Language Model (COLING2020)☆120Updated 4 years ago
- DialogSum: A Real-life Scenario Dialogue Summarization Dataset - Findings of ACL 2021☆179Updated 8 months ago
- ☆42Updated 4 years ago
- A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approa…☆97Updated 3 years ago
- Official Implementation of "DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization."☆141Updated 2 years ago
- Implementation of Self-adjusting Dice Loss from "Dice Loss for Data-imbalanced NLP Tasks" paper☆108Updated 4 years ago
- [EMNLP 2021] LM-Critic: Language Models for Unsupervised Grammatical Error Correction☆119Updated 3 years ago
- Long-context pretrained encoder-decoder models☆96Updated 2 years ago
- Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (ACL 2021)☆30Updated 2 years ago
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆48Updated 3 years ago
- ☆47Updated 2 years ago
- The official code of the "Frustratingly Easy System Combination for Grammatical Error Correction" paper☆56Updated last year
- The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)☆53Updated 3 years ago
- SpanNER: Named EntityRe-/Recognition as Span Prediction☆132Updated 3 years ago
- A long version of BART model based on Longformer model☆23Updated 2 years ago
- A Light and Modular PyTorch NLP Project Template☆59Updated 4 years ago
- [EMNLP 2021] Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification☆129Updated 2 years ago
- The Few-Shot Bot: Prompt-Based Learning for Dialogue Systems☆118Updated 3 years ago
- ☆66Updated 3 years ago
- This is the official code for Extractive Summarization of Long Documents by Combining Global and Local Context☆69Updated 4 years ago
- Official PyTorch Implementation of SSMix (Findings of ACL 2021)☆62Updated 4 years ago
- ☆78Updated last year
- [EMNLP 2021] Improving and Simplifying Pattern Exploiting Training☆153Updated 3 years ago