Papers with unsupervised pretraining
Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation (P19-2)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) uses sequence to sequence architectures, but requires a huge amount of parallel data. |
| Approach: | They use Elastic Weight Consolidation to regularize weights of two language models . they then fine-tune the model on parallel data to avoid forgetting the original task . |
| Outcome: | The proposed method achieves BLEU scores similar to the previous work, but is slower and requires less training data. |
Generative Text Modeling through Short Run Inference (2021.eacl-main)
Copied to clipboard
| Challenge: | Latent variable models for text capture global semantic and syntactic features when trained correctly. |
| Approach: | They propose a short run dynamics for inference that initializes from the prior distribution of the latent variable and runs a small number of Langevin dynamics steps guided by its posterior distribution. |
| Outcome: | The proposed model is able to generate coherent sentences with smooth transition and shows no sign of posterior collapse. |
Inexpensive Domain Adaptation of Pretrained Language Models: Case Studies on Biomedical NER and Covid-19 QA (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained Language Models (PTLMs) are typically pretraining on target-domain text, which is expensive in terms of hardware, runtime and CO 2 emissions. |
| Approach: | They propose a faster, CPU-only domainadaptation method that trains Word2Vec on target-domain text and aligns the resulting word vectors with the wordpiece vectors of a general-domain PTLM. |
| Outcome: | The proposed method covers 60% of the BioBERT - BERT F1 delta, 5% of BioBERTS’s CO2 footprint and 2% of its cloud compute cost. |
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases (2022.lrec-1)
Copied to clipboard
| Challenge: | MUSS trains strong models using sentence-level paraphrase data instead of labeled simplification data. |
| Approach: | They propose a multilingual unsupervised sentence simplification system that does not require labeled simplification data. |
| Outcome: | The proposed model outperforms the previous best supervised models on English, French, and Spanish benchmarks despite not using labeled simplification data. |
Learning to Retrieve Passages without Supervision (2022.naacl-main)
Copied to clipboard
| Challenge: | Dense retrievers for open domain question answering have been shown to achieve impressive performance by training on large datasets of question-passage pairs. |
| Approach: | They propose to use recurring spans to create pseudo examples for contrastive learning. |
| Outcome: | The proposed model outperforms all pretrained baselines on a wide range of ODQA datasets and is competitive with BM25, a strong sparse baseline. |
mDAPT: Multilingual Domain Adaptive Pretraining in a Single Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific multilingual pretraining data is difficult to obtain due to regulations, legislation, or simply a lack of language- and domain- specific text. |
| Approach: | They propose to continue pretraining a language model on domain-specific unlabelled text . this allows for better modelling of text for downstream tasks within the domain . |
| Outcome: | The proposed approach outperforms the general multilingual model and performs close to its monolingual counterpart. |