matthew-cavener / my-bert-is-too-big
Doing Knowledge Distillation on BERT because the inference time is too damn high!
☆9Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for my-bert-is-too-big
- ☆22Updated 3 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
- NAACL'19: "Jointly Optimizing Diversity and Relevance in Neural Response Generation"☆74Updated 4 years ago
- A generic library for crafting adversarial NLP examples - WIP☆40Updated 6 years ago
- A lightweight but powerful library to build token indices for NLP tasks, compatible with major Deep Learning frameworks like PyTorch and …☆49Updated 4 years ago
- ☆30Updated 4 years ago
- Code for SIGDial 2019 Best Paper: Structured Fusion Networks for Dialog https://arxiv.org/abs/1907.10016☆31Updated 5 years ago
- Tools for training pytorch language models☆27Updated 4 years ago
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆52Updated 4 years ago
- ☆32Updated 5 years ago
- Stacked Denoising BERT for Noisy Text Classification (Neural Networks 2020)☆32Updated 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
- We are creating a challenging new benchmark MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models. Retrieval quest…☆30Updated 4 years ago
- Boolean Question Answering with multi-task learning and uses large LM embeddings like BERT, RoBERTa☆18Updated 5 years ago
- Author implementation of "Learning to Search in Long Documents Using Document Structure" (Mor Geva and Jonathan Berant, 2018)☆22Updated 6 years ago
- pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference☆61Updated last year
- ☆33Updated 6 years ago
- EMNLP'2018: Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering☆25Updated 5 years ago
- source code of bison☆26Updated 4 years ago
- Pre-training character n-gram embeddings☆23Updated last year
- A novel method of constrained decoding for neural NLG (NNLG) models☆84Updated 4 years ago
- NoiseMix - data generation for natural language☆41Updated 6 years ago
- ☆20Updated 4 years ago
- ☆61Updated 5 years ago
- Frame-Semantic and PropBank Semantic Role Labeling with Syntactic Scaffolding.☆50Updated 3 years ago
- The Referential Reader: A Recurrent Entity Network for Anaphora Resolution, published at ACL 2019☆19Updated 5 years ago
- Code for EMNLP 2019 paper "Modeling Multi-Action Policy for Task-Oriented Dialogues"☆19Updated 5 years ago
- ☆31Updated 5 years ago
- ☆41Updated 5 years ago
- LM, ULMFit et al.☆47Updated 4 years ago