samsucik / knowledge-distil-bert
Master's thesis project in collaboration with Rasa, focusing on knowledge distillation from BERT into different very small networks and analysis of the students' NLP capabilities.
☆13Updated 2 years ago
Alternatives and similar repositories for knowledge-distil-bert:
Users that are interested in knowledge-distil-bert are comparing it to the libraries listed below
- This repository contains datasets and code for the paper "HINT3: Raising the bar for Intent Detection in the Wild" accepted at EMNLP-2020…☆33Updated 4 years ago
- A simple neural truecaser written in pytorch and allennlp.☆33Updated 10 months ago
- ☆49Updated 3 years ago
- Generative Retrieval Transformer☆28Updated last year
- A Benchmark Dataset for Understanding Disfluencies in Question Answering☆62Updated 3 years ago
- Parallelized automatic corpus collection for ASR. Forked from https://github.com/EgorLakomkin/KTSpeechCrawler☆23Updated 4 years ago
- Many Natural Language Processing tasks rely on sentence boundary detection (SBD). Although amazing libraries like spacy provide state of …☆61Updated 4 years ago
- ☆33Updated 6 years ago
- ☆16Updated last year
- The implementation of the papers on dual learning of natural language understanding and generation. (ACL2019,2020; Findings of EMNLP 2020…☆66Updated 4 years ago
- Stacked Denoising BERT for Noisy Text Classification (Neural Networks 2020)☆32Updated 2 years ago
- zero-vocab or low-vocab embeddings☆18Updated 2 years ago
- ☆56Updated 3 years ago
- a Fairseq fork for sequence tagging/labeling tasks☆31Updated 4 years ago
- Assessing syntactic abilities of BERT☆39Updated 5 years ago
- BERT models for many languages created from Wikipedia texts☆33Updated 4 years ago
- A step-by-step problem set for implementing a high-quality deep dependency parser in Pytorch☆15Updated 7 years ago
- A repository linking to publicly available dialog datasets. Feel free to send pull requests.☆68Updated 3 years ago
- Code for the paper: Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries☆19Updated 3 years ago
- Tokenization across languages. Useful as preprocessing for subword tokenization.☆22Updated 2 years ago
- A crowdsourced dataset of dialogues grounded in social contexts involving utilization of commonsense.☆78Updated 3 years ago
- ☆33Updated 3 years ago
- This code provides word level language identification tool for identifying language for individual words in Code-Mixed text. e.g. The tex…☆54Updated 4 years ago
- Pre-trained models and code and data to train and use models from "Pushing the Limits of Paraphrastic Sentence Embeddings with Millions o…☆101Updated last year
- Contains all teaching material used in ACL 2020 Tutorial "Reviewing NLP" given on July 5 2020☆18Updated 4 years ago
- ☆30Updated 4 years ago
- ☆27Updated 6 years ago
- ☆32Updated 5 years ago
- Fine-tune transformers with pytorch-lightning☆44Updated 3 years ago
- Implementation of Z-BERT-A: a zero-shot pipeline for unknown intent detection.☆39Updated last year