matthew-cavener / my-bert-is-too-bigLinks
Doing Knowledge Distillation on BERT because the inference time is too damn high!
☆9Updated 5 years ago
Alternatives and similar repositories for my-bert-is-too-big
Users that are interested in my-bert-is-too-big are comparing it to the libraries listed below
Sorting:
- Boolean Question Answering with multi-task learning and uses large LM embeddings like BERT, RoBERTa☆18Updated 5 years ago
- Tools for training pytorch language models☆27Updated 4 years ago
- ☆46Updated 5 years ago
- Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation☆63Updated 6 years ago
- ☆22Updated 3 years ago
- a Fairseq fork for sequence tagging/labeling tasks☆31Updated 5 years ago
- NoiseMix - data generation for natural language☆40Updated 7 years ago
- pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference☆62Updated 2 years ago
- Companion site for "Analysis Methods in Neural Language Processing: A Survey"☆66Updated 5 years ago
- A generic library for crafting adversarial NLP examples - WIP☆41Updated 6 years ago
- A framework for training and evaluating AI models on a variety of openly available dialogue datasets.☆36Updated 4 years ago
- ☆31Updated 6 years ago
- PyTorch implementation of context2vec from Melamud et al., CoNLL 2016☆19Updated 6 years ago
- ☆20Updated 5 years ago
- NAACL'19: "Jointly Optimizing Diversity and Relevance in Neural Response Generation"☆74Updated 4 years ago
- Assessing syntactic abilities of BERT☆148Updated 6 years ago
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆51Updated 5 years ago
- The implementation of the papers on dual learning of natural language understanding and generation. (ACL2019,2020; Findings of EMNLP 2020…☆66Updated 4 years ago
- A novel method of constrained decoding for neural NLG (NNLG) models☆83Updated 4 years ago
- Stacked Denoising BERT for Noisy Text Classification (Neural Networks 2020)☆32Updated 2 years ago
- Pre-training character n-gram embeddings☆22Updated last year
- ☆35Updated 3 years ago
- a Pytorch implementation of the Reformer Network (https://openreview.net/pdf?id=rkgNKkHtvB)☆53Updated 2 years ago
- ☆33Updated 7 years ago
- The accompanying code for "Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understandin…☆21Updated 5 years ago
- Phrase-Indexed Question Answering (PIQA)☆94Updated 6 years ago
- ☆32Updated 6 years ago
- A template for starting an allennlp project using a python script instead of config files☆27Updated last year
- Official implementation of the models proposed in paper "Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss"☆19Updated 6 years ago
- Fine-tuned Transformers compatible BERT models for Sequence Tagging☆40Updated 4 years ago