fe1ixxu / Intra-Distillation
This is the repository for our EMNLP 2022 paper "The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains".
☆10Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Intra-Distillation
- Code and Data release for "Improving Multilingual Translation by Representation and Gradient Regularization" (Yang et al. EMNLP 2021), an…☆13Updated 3 months ago
- [NeurIPS 2021] Duplex Sequence-to-Sequence Learning for Reversible Machine Translation☆14Updated 2 years ago
- ☆13Updated 3 years ago
- ☆11Updated 3 years ago
- Instruction to data diversification☆24Updated 3 years ago
- Code for NeurIPS 2022 Spotlight paper " Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation"☆20Updated last year
- ☆20Updated 3 years ago
- ☆59Updated 2 years ago
- A retrieval augmented sequence modeling toolkit implemented based on Fairseq☆29Updated last year
- No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models (ICLR 2022)☆29Updated 2 years ago
- Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"☆23Updated 3 years ago
- ☆23Updated last year
- Code for the ICLR'22 paper "Improving Non-Autoregressive Translation Models Without Distillation"☆17Updated 2 years ago
- Official Implementation for the ICLR2023 paper "Fuzzy Alignments in Directed Acyclic Graph for Non-autoregressive Machine Translation"☆13Updated last year
- The implementation of "Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Deco…☆32Updated 9 months ago
- Small utility to monitor fairseq training in tensorboard☆21Updated 5 years ago
- ☆20Updated 4 years ago
- Implementation of our paper "Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation" in EMNLP-2020.☆23Updated 3 years ago
- ☆95Updated 2 years ago
- Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)☆24Updated 3 years ago
- ☆84Updated last year
- Introduction and scripts for ACL-2020 paper "On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation"☆21Updated 4 years ago
- ☆44Updated 3 years ago
- Code and data accompanying our ACL 2020 paper, "Unsupervised Domain Clusters in Pretrained Language Models".☆59Updated 4 years ago
- This is the repository of the EMNLP 2021 paper "BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translati…☆31Updated last year
- Code for paper "Nearest Neighbor Knowledge Distillation for Neural Machine Translation" by Zhixian Yang, Renliang Sun, and Xiaojun Wan. T…☆30Updated 2 years ago
- LLM4MT☆10Updated 6 months ago
- Code for NeurIPS2020 "Incorporating BERT into Parallel Sequence Decoding with Adapters"☆32Updated 2 years ago
- Data and code accompanying the paper "As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive…☆21Updated last year
- ☆24Updated 4 months ago